© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 10503
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling and character development in literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "of" when it appears in descriptive phrases about stories, tales, or narratives (especially in book descriptions and reviews).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    relational function words—especially prepositions—that link nouns or clauses (e.g., indicating “of/about”-type relationships).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peg
    -0.16
    usch
    -0.16
    ÙĪار
    -0.15
    Zero
    -0.15
    DonaldTrump
    -0.14
    edList
    -0.14
     Enemies
    -0.14
    ogan
    -0.14
    á»ĥ
    -0.14
    _cred
    -0.14
    POSITIVE LOGITS
     how
    0.17
     change
    0.14
     repeat
    0.14
     life
    0.13
    ç«
    0.13
     inter
    0.13
     not
    0.13
     trim
    0.13
     Eis
    0.13
     Ont
    0.13
    Activations Density 0.077%

    No Known Activations