© 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. 55208
    Prev
    Next
    INDEX
    Explanations

    instances of self-admission or acknowledgment in discussions

    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
    PAD
    -0.07
    Ìĥ
    -0.07
    switch
    -0.07
    anova
    -0.06
    iveau
    -0.06
    aub
    -0.06
    er
    -0.06
    arc
    -0.06
    ر
    -0.06
    oog
    -0.06
    POSITIVE LOGITS
     rằng
    0.08
     admitted
    0.08
    icode
    0.07
    /assert
    0.07
     defeat
    0.07
    ably
    0.07
    rica
    0.07
     that
    0.07
    æĸĻ
    0.07
    /disc
    0.07
    Activations Density 0.010%

    No Known Activations