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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 1594
    Prev
    Next
    INDEX
    Explanations

    references to visual imagery and descriptive features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ameda
    -0.15
     Twilight
    -0.15
    423
    -0.15
     skimage
    -0.14
    409
    -0.14
    adius
    -0.14
    ppy
    -0.14
     McMaster
    -0.14
     built
    -0.14
    uid
    -0.14
    POSITIVE LOGITS
     sinister
    0.24
     Dexter
    0.23
     argent
    0.23
     quarterly
    0.21
    zure
    0.21
     Supporters
    0.20
     charges
    0.20
    azon
    0.20
    argent
    0.20
     azure
    0.20
    Activations Density 0.012%

    No Known Activations