© 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. 73225
    Prev
    Next
    INDEX
    Explanations

    references to specific identifiers or categories, perhaps related to datasets or tags

    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
    acias
    -0.07
    ndon
    -0.07
    uhan
    -0.07
    Anonymous
    -0.07
    krom
    -0.06
    elden
    -0.06
    655
    -0.06
    utton
    -0.06
    iej
    -0.06
     Anonymous
    -0.06
    POSITIVE LOGITS
    èĪŀ
    0.06
    596
    0.06
    guards
    0.06
    tam
    0.06
     Meer
    0.06
    embre
    0.06
    121
    0.06
    120
    0.06
    Dll
    0.06
    ucchini
    0.06
    Activations Density 0.006%

    No Known Activations