© 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. 107756
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly those that involve event handling and registration

    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
    usher
    -0.07
    uto
    -0.06
    loy
    -0.06
    ÑĢап
    -0.06
    .raise
    -0.06
    ursal
    -0.06
    odel
    -0.06
    osc
    -0.06
    atar
    -0.06
    AVA
    -0.06
    POSITIVE LOGITS
    USAGE
    0.11
    Usage
    0.11
     Usage
    0.10
     usage
    0.10
     USAGE
    0.10
    usage
    0.09
    _usage
    0.08
    _USAGE
    0.07
    alon
    0.07
     callers
    0.07
    Activations Density 0.017%

    No Known Activations