© 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. 86579
    Prev
    Next
    INDEX
    Explanations

    curly braces and other code structure indicators

    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
     ç¨
    -0.07
     dosp
    -0.07
    igham
    -0.06
    ì¦Į
    -0.06
    iol
    -0.06
    uta
    -0.06
     Parker
    -0.06
    @endforeach
    -0.06
    dana
    -0.06
    ÑĢаÑģ
    -0.06
    POSITIVE LOGITS
     private
    0.09
    private
    0.07
    (private
    0.07
    entar
    0.07
    (/^\
    0.07
     public
    0.07
    issance
    0.07
     protected
    0.06
     /**č↵
    0.06
     progress
    0.06
    Activations Density 0.004%

    No Known Activations