© 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. 39683
    Prev
    Next
    INDEX
    Explanations

    the term "Do" used in various contexts, indicating a focus on the concept of "doing" or actions

    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
    venge
    -0.07
    anger
    -0.07
    nost
    -0.07
    ulous
    -0.07
    ulously
    -0.06
    биÑĢа
    -0.06
    kom
    -0.06
    bens
    -0.06
    gio
    -0.06
    anness
    -0.06
    POSITIVE LOGITS
    zens
    0.11
    žel
    0.08
    berman
    0.08
    ovie
    0.08
    ctype
    0.07
    xygen
    0.07
    ogie
    0.07
    linger
    0.07
    anta
    0.07
    ximity
    0.07
    Activations Density 0.022%

    No Known Activations