© 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. 94901
    Prev
    Next
    INDEX
    Explanations

    issues related to ethics and justice

    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
     mest
    -0.07
    uma
    -0.06
    lex
    -0.06
    ↵↵
    -0.06
    .truth
    -0.06
    edException
    -0.06
    ék
    -0.06
    rec
    -0.06
     tall
    -0.06
     Platt
    -0.06
    POSITIVE LOGITS
    ergus
    0.07
    .interval
    0.07
    asti
    0.07
    ppelin
    0.07
    uard
    0.07
    .Companion
    0.07
    _NB
    0.07
    aphrag
    0.06
    asaki
    0.06
    881
    0.06
    Activations Density 0.309%

    No Known Activations