© 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 EvalsExportsAPI 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. 29266
    Prev
    Next
    INDEX
    Explanations

    references to legislative or governmental actions and discussions

    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
    üz
    -0.07
     Superintendent
    -0.07
    .batch
    -0.07
    jis
    -0.06
     Mellon
    -0.06
     Regents
    -0.06
    /board
    -0.06
    liable
    -0.06
    iones
    -0.06
    озем
    -0.06
    POSITIVE LOGITS
     Shadow
    0.09
    Shadow
    0.08
     party
    0.08
     Whip
    0.08
     hol
    0.07
     shadow
    0.07
     motion
    0.07
     Commons
    0.07
     MPs
    0.07
    Hol
    0.07
    Activations Density 0.075%

    No Known Activations