© 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. 41614
    Prev
    Next
    INDEX
    Explanations

    patterns or formatting within the document's structure

    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
    ochond
    -0.07
    eworthy
    -0.07
    ekler
    -0.07
    GetMethod
    -0.07
    cdb
    -0.07
    ĴĮ
    -0.07
    âĢ¦.↵↵
    -0.06
     VÄĽ
    -0.06
     ðŁĺī↵↵
    -0.06
    Trivia
    -0.06
    POSITIVE LOGITS
    onte
    0.06
    _UNUSED
    0.06
    Sep
    0.06
    ona
    0.06
    ème
    0.06
    ocker
    0.06
     gang
    0.06
    âij
    0.05
     gerek
    0.05
    <li
    0.05
    Activations Density 0.009%

    No Known Activations