© 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. 92635
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or collective action within a community

    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
    	Copyright
    -0.09
    andon
    -0.08
    вÑĸÑĤ
    -0.07
     Ä°Åŀ
    -0.07
    PÅĻed
    -0.07
     Apocalypse
    -0.07
    allest
    -0.07
    ousel
    -0.07
    γκο
    -0.07
    lé
    -0.07
    POSITIVE LOGITS
    're
    0.12
    've
    0.12
    ’re
    0.11
    'll
    0.11
    ’ve
    0.10
     are
    0.10
    eping
    0.10
    ’ll
    0.09
     can
    0.09
    'd
    0.09
    Activations Density 0.261%

    No Known Activations