© 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. 120777
    Prev
    Next
    INDEX
    Explanations

    patterns and symbols related to code syntax and file structures

    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
    igy
    -0.07
    .ide
    -0.06
    åıĸ
    -0.06
    аÑģÑģив
    -0.06
    ulen
    -0.06
    ÑĤен
    -0.06
    -ÑĤо
    -0.06
     CALLBACK
    -0.06
     wonder
    -0.05
    AINER
    -0.05
    POSITIVE LOGITS
    ieg
    0.07
    =<?=$
    0.07
    _except
    0.07
    .IsAny
    0.06
    Ĥ¨
    0.06
     except
    0.06
     Ñĥгод
    0.06
    ellan
    0.06
    .Toolkit
    0.06
    ostream
    0.06
    Activations Density 0.002%

    No Known Activations