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

    Neuronpedia

    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. 7445
    Prev
    Next
    INDEX
    Explanations

    references to artificial or synthetic materials

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

    the word "artificial" when describing manufactured or synthetic materials and objects.

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

    mentions of man-made or synthetic materials, surfaces, and constructs rather than natural ones.

    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
    stag
    -0.17
    athers
    -0.15
    lane
    -0.15
    usz
    -0.14
    shire
    -0.14
    ãģĵãĤį
    -0.14
    ric
    -0.14
     blind
    -0.14
     Mattis
    -0.14
    uš
    -0.14
    POSITIVE LOGITS
    /false
    0.18
    umann
    0.16
    erte
    0.15
    ODO
    0.15
    Exact
    0.15
    jour
    0.15
    CONN
    0.15
    233
    0.15
     exact
    0.15
    (fake
    0.15
    Activations Density 0.058%

    No Known Activations