© 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. 94704
    Prev
    Next
    INDEX
    Explanations

    phrases indicating current circumstances or conditions

    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
    áž
    -0.07
    aze
    -0.07
    beg
    -0.07
    Disclaimer
    -0.06
    ent
    -0.06
    ized
    -0.06
    SEA
    -0.06
    izer
    -0.06
    175
    -0.06
     each
    -0.06
    POSITIVE LOGITS
     Eudicots
    0.08
    adoo
    0.08
    ãĥªãĤ¹
    0.07
    ibur
    0.07
    _OT
    0.07
    ÑĢиÑģ
    0.07
    ÃŃcul
    0.07
    ÑĥмÑĥ
    0.07
    ãĥ¼ãĥĨãĤ£
    0.07
    гаÑĢ
    0.07
    Activations Density 0.021%

    No Known Activations