© 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. 124642
    Prev
    Next
    INDEX
    Explanations

    references to specific groups of people or populations in various contexts

    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
    ÑĢог
    -0.07
     Gamb
    -0.06
    ltk
    -0.06
    rium
    -0.06
    ниÑĤелÑĮ
    -0.06
     Suc
    -0.06
    achu
    -0.06
    acie
    -0.06
    prav
    -0.06
    lant
    -0.06
    POSITIVE LOGITS
    umm
    0.08
    rene
    0.07
     into
    0.07
    (Adapter
    0.06
    zig
    0.06
    oker
    0.06
    /rc
    0.06
    ults
    0.06
    into
    0.06
    ulg
    0.06
    Activations Density 0.084%

    No Known Activations