© 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. 107992
    Prev
    Next
    INDEX
    Explanations

    instances of class initialization methods and related function definitions

    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
    unsch
    -0.09
    μί
    -0.07
    imit
    -0.07
    kie
    -0.07
    phies
    -0.07
    gross
    -0.07
    彦
    -0.06
    akin
    -0.06
    lopen
    -0.06
    oun
    -0.06
    POSITIVE LOGITS
    úsqueda
    0.08
    ¬
    0.07
    917
    0.06
    urtle
    0.06
     reel
    0.06
    ENU
    0.06
    WithMany
    0.06
    ORA
    0.06
    /init
    0.06
     seal
    0.06
    Activations Density 0.000%

    No Known Activations