© 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. 123924
    Prev
    Next
    INDEX
    Explanations

    references to data handling and processing in code

    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
    rup
    -0.07
    inker
    -0.06
    bum
    -0.06
     pys
    -0.06
    irty
    -0.06
    ÑĪÑĤ
    -0.06
     hy
    -0.06
    erman
    -0.06
    ric
    -0.06
     dispersion
    -0.05
    POSITIVE LOGITS
    raž
    0.08
    èģĶç½ij
    0.07
    nothrow
    0.07
    еко
    0.07
    Ïĥί
    0.07
    .apps
    0.07
    èĹ
    0.07
    _ASSUME
    0.07
    Vectorizer
    0.06
    ongan
    0.06
    Activations Density 0.009%

    No Known Activations