© 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. 16386
    Prev
    Next
    INDEX
    Explanations

    professions and roles related to creativity, art, and activism

    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
    ala
    -0.07
    imm
    -0.07
    ime
    -0.07
    èĮ
    -0.07
    atta
    -0.07
    ander
    -0.07
    lyn
    -0.06
     Berm
    -0.06
    adera
    -0.06
    arda
    -0.06
    POSITIVE LOGITS
     बनन
    0.09
    panion
    0.08
    hood
    0.07
    ailable
    0.07
    ship
    0.06
    SHIP
    0.06
    ~-~-
    0.06
    actionDate
    0.06
    _putchar
    0.06
    /WebAPI
    0.06
    Activations Density 0.050%

    No Known Activations