© 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. 15-LLAMASCOPE-RES-131K
    11. 88882
    Prev
    Next
    INDEX
    Explanations

    the name "Wilson" and its variations, indicating a focus on specific individuals or characters associated with that name

    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
    intree
    -0.08
     dikke
    -0.07
    RuntimeObject
    -0.07
    elman
    -0.07
    ä¸įåĪ°
    -0.07
    elry
    -0.07
    ipi
    -0.07
    -INFRINGEMENT
    -0.07
    ñana
    -0.07
    à¤ľà¤¨
    -0.07
    POSITIVE LOGITS
    s
    0.09
    iard
    0.09
     ApplicationException
    0.07
    redient
    0.06
    gram
    0.06
    ene
    0.06
    r
    0.06
    ars
    0.06
     Fraser
    0.06
    walker
    0.06
    Activations Density 0.007%

    No Known Activations