© 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 EvalsExportsAPI 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. 56127
    Prev
    Next
    INDEX
    Explanations

    the name "Cecil" and related variants or occurrences in the text

    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
    escaped
    -0.07
    Äįel
    -0.07
    ména
    -0.07
    alse
    -0.06
    abus
    -0.06
    HEL
    -0.06
    inbox
    -0.06
    estar
    -0.06
    Wheel
    -0.06
    elik
    -0.06
    POSITIVE LOGITS
    los
    0.07
    lla
    0.07
    ized
    0.07
    ouser
    0.07
    ution
    0.07
     Infinite
    0.07
    ised
    0.07
    uil
    0.07
    ĶåĽŀ
    0.07
    shaft
    0.06
    Activations Density 0.010%

    No Known Activations