© 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. 4489
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to elections and governance

    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
    llen
    -0.07
    uchos
    -0.07
    ivec
    -0.07
    utzer
    -0.07
    ãĥ¬ãĥ³
    -0.06
    ÏĢά
    -0.06
    åijĢ
    -0.06
    enty
    -0.06
    zcze
    -0.06
     giả
    -0.06
    POSITIVE LOGITS
     could
    0.08
     nothing
    0.08
     amount
    0.08
    amount
    0.08
     NOTHING
    0.07
    could
    0.07
     Nothing
    0.07
     Amount
    0.07
    Nothing
    0.07
     short
    0.07
    Activations Density 0.061%

    No Known Activations