© 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. 17681
    Prev
    Next
    INDEX
    Explanations

    mentions of origins and causes related to investigations or inquiries

    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
    bad
    -0.06
    roma
    -0.06
     GDPR
    -0.06
    544
    -0.06
     bad
    -0.05
     preview
    -0.05
    abox
    -0.05
     Muse
    -0.05
     Scout
    -0.05
    918
    -0.05
    POSITIVE LOGITS
    mass
    0.07
     tower
    0.07
     trailers
    0.07
    |array
    0.07
    /tiny
    0.07
    mind
    0.07
    ****************************************************************************
    0.07
    wij
    0.07
    .frames
    0.07
    urr
    0.07
    Activations Density 0.002%

    No Known Activations