© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 79677
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tro
    -0.06
     tro
    -0.06
    wishlist
    -0.06
    undry
    -0.06
    елÑĮ
    -0.06
    tro
    -0.06
    ÏĦÏİν
    -0.06
    /locale
    -0.06
    rella
    -0.06
    TableRow
    -0.06
    POSITIVE LOGITS
    odem
    0.08
    ardy
    0.07
    rzy
    0.07
    unami
    0.07
    uang
    0.07
    nock
    0.07
    	Il
    0.07
    vince
    0.07
     Shemale
    0.07
    hower
    0.07
    Activations Density 0.010%

    No Known Activations