© 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. 105413
    Prev
    Next
    INDEX
    Explanations

    numerical forecasts and projections related to viewership, sales, and commodities

    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
    quier
    -0.07
    ëĭ´
    -0.07
    è±
    -0.07
    emachine
    -0.06
    _HT
    -0.06
     ná
    -0.06
    alic
    -0.06
     FIX
    -0.06
    ãĥīãĥ«
    -0.06
    æ¿ĥ
    -0.06
    POSITIVE LOGITS
     year
    0.09
    ä»Ĭå¹´
    0.09
     Year
    0.08
    -year
    0.08
    year
    0.08
    年度
    0.07
    /archive
    0.07
     season
    0.07
     tonight
    0.07
    Year
    0.07
    Activations Density 0.060%

    No Known Activations