© 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. 72755
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions and maps

    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
    ednou
    -0.07
    -chan
    -0.06
    itone
    -0.06
     Tavern
    -0.06
     Tamb
    -0.06
    Ñıл
    -0.06
    elve
    -0.06
    .sy
    -0.06
    elix
    -0.05
    ason
    -0.05
    POSITIVE LOGITS
    adiens
    0.07
    duto
    0.06
     endregion
    0.06
    jÃŃž
    0.06
    igua
    0.06
    igu
    0.06
    ï¼Ĵ
    0.06
    lew
    0.06
    pillar
    0.06
    igue
    0.06
    Activations Density 0.017%

    No Known Activations