© 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. 92910
    Prev
    Next
    INDEX
    Explanations

    references to Arthurian legends and related characters

    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
    omi
    -0.08
     Zeus
    -0.06
     Athens
    -0.06
    aminer
    -0.06
    odied
    -0.06
    prit
    -0.06
     NSRange
    -0.06
    äs
    -0.06
     sav
    -0.06
     Dickens
    -0.06
    POSITIVE LOGITS
    åĨĨ
    0.09
    Legendary
    0.08
    England
    0.07
     Leicester
    0.07
     tournaments
    0.07
     åĨĨ
    0.07
     tournament
    0.07
     Welsh
    0.07
     Wales
    0.07
     England
    0.07
    Activations Density 0.007%

    No Known Activations