© 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. 31220
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies and their members

    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
    ivol
    -0.06
    vez
    -0.06
    _PRIVATE
    -0.06
    reak
    -0.06
    datatable
    -0.06
     Venez
    -0.06
     pending
    -0.06
     Tel
    -0.06
    alta
    -0.06
    dej
    -0.06
    POSITIVE LOGITS
     indirectly
    0.08
     Seats
    0.08
    plorer
    0.08
    stoff
    0.08
     indirect
    0.08
    ãĥ¼ãĥ«ãĥī
    0.07
     seats
    0.07
    AREST
    0.07
    ican
    0.07
    Seats
    0.07
    Activations Density 0.012%

    No Known Activations