© 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. 93013
    Prev
    Next
    INDEX
    Explanations

    references to types and classifications

    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
    ing
    -0.06
    h
    -0.06
    ,
    -0.05
     PRI
    -0.05
     U
    -0.05
     av
    -0.05
    hs
    -0.05
    ree
    -0.05
     personal
    -0.05
    -
    -0.05
    POSITIVE LOGITS
    dech
    0.08
     /**č↵
    0.08
    styleType
    0.08
     /*č↵
    0.07
     automát
    0.07
    bote
    0.07
    Overflow
    0.07
    Č↵
    0.07
    alim
    0.07
    ãģĹãģ¦ãĤĭ
    0.07
    Activations Density 0.011%

    No Known Activations