© 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. 17529
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Paul Whiteman."

    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
    داÙĨ
    -0.06
     ÚĨت
    -0.06
    .getInteger
    -0.06
    Å¡li
    -0.06
    ÐĦ
    -0.06
    ITCH
    -0.06
     ÙģصÙĦ
    -0.06
    ritz
    -0.06
    urn
    -0.06
    lovak
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.07
    imedia
    0.07
    bsolute
    0.06
    pector
    0.06
    icast
    0.06
     Harr
    0.06
    aceae
    0.06
     Rodriguez
    0.06
    ouser
    0.06
    modo
    0.06
    Activations Density 0.023%

    No Known Activations