© 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. 92327
    Prev
    Next
    INDEX
    Explanations

    occurrences of dates and numerical data

    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
    709
    -0.07
     sag
    -0.06
    urch
    -0.06
    aste
    -0.06
     Sag
    -0.06
    539
    -0.06
    abet
    -0.06
    idar
    -0.06
    CallCheck
    -0.06
     subs
    -0.05
    POSITIVE LOGITS
    zyst
    0.07
    utzer
    0.07
    .utf
    0.07
    ç¾
    0.07
    _convert
    0.06
     ìĺ¤íĽĦ
    0.06
    UTF
    0.06
    bourne
    0.06
    æĻ´
    0.06
    ìħ
    0.06
    Activations Density 0.010%

    No Known Activations