© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 70751
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical graphs and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical tokens in code and mathematical expressions, often representing function calls, variable references, or symbolic notation in specialized contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    bsites
    -0.08
     (
    -0.07
    UpInside
    -0.07
    -0.07
     ostensibly
    -0.07
     intimately
    -0.06
     modest
    -0.06
    Âł
    -0.06
     *
    -0.06
    /***/
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵↵↵↵
    0.11
    .↵↵↵↵↵↵↵↵↵↵
    0.10
     arac
    0.10
    евÑĸ
    0.10
    ’Ñıз
    0.10
     servis
    0.10
    .same
    0.10
    !↵↵↵↵
    0.10
    оÑĢÑĸ
    0.10
    .attachment
    0.09
    Activations Density 8.232%

    No Known Activations