© 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. 9-LLAMASCOPE-RES-131K
    11. 94430
    Prev
    Next
    INDEX
    Explanations

    references to self-service and password management tools

    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
     Levine
    -0.06
     epis
    -0.06
    æ³¥
    -0.06
     spd
    -0.06
     Doc
    -0.06
    ãģ¤ãģ¶
    -0.05
    atched
    -0.05
     doc
    -0.05
    YK
    -0.05
    ATCH
    -0.05
    POSITIVE LOGITS
    /self
    0.09
    ibold
    0.07
    ahlen
    0.07
    -self
    0.07
    quate
    0.07
    elik
    0.07
    errorCode
    0.07
    eroon
    0.07
    eln
    0.06
     Self
    0.06
    Activations Density 0.003%

    No Known Activations