© 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. 120359
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and self-referential language

    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
    (targetEntity
    -0.07
    SOLE
    -0.06
    aya
    -0.06
     invariant
    -0.06
    olest
    -0.06
    cop
    -0.06
     Aeros
    -0.06
    çħ§
    -0.06
    UCH
    -0.06
    licit
    -0.06
    POSITIVE LOGITS
    iddles
    0.06
    ulers
    0.06
    CONDS
    0.06
    _SCR
    0.06
    aeper
    0.06
    ázd
    0.06
    ,exports
    0.06
    isson
    0.06
    /errors
    0.06
    aln
    0.06
    Activations Density 0.003%

    No Known Activations