© 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. 95227
    Prev
    Next
    INDEX
    Explanations

    articles indicating quantities or classifications related to groups or items

    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
    _mB
    -0.08
    ç´ł
    -0.07
    reesome
    -0.07
    ÑĢал
    -0.07
    alyze
    -0.07
    åł
    -0.07
    /Dk
    -0.07
    .Txt
    -0.07
    ع
    -0.06
    æŃ
    -0.06
    POSITIVE LOGITS
     effort
    0.11
     attempt
    0.10
     move
    0.09
     bid
    0.08
     sign
    0.07
     testament
    0.07
     nod
    0.07
     act
    0.07
     efforts
    0.07
    attempt
    0.07
    Activations Density 0.016%

    No Known Activations