© 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. 92647
    Prev
    Next
    INDEX
    Explanations

    instances of self-referential language and self-evaluation

    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
    una
    -0.07
    164
    -0.06
    leo
    -0.06
     stringstream
    -0.06
    amer
    -0.06
    .LookAndFeel
    -0.06
    Columns
    -0.06
    769
    -0.06
    inheritDoc
    -0.06
    ari
    -0.06
    POSITIVE LOGITS
    auc
    0.08
    ultiply
    0.08
    stown
    0.07
    koa
    0.07
    yte
    0.07
    olutely
    0.07
    /misc
    0.07
    ìĦŃ
    0.07
    اÙĨÛĮا
    0.07
     Abrams
    0.06
    Activations Density 0.008%

    No Known Activations