© 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. 81102
    Prev
    Next
    INDEX
    Explanations

    numerical data represented in a structured format

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

    Tokens that appear in sequences, primarily consecutive numbers, punctuation marks, or specific contextual elements that form part of a structured document or content format.

    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
    UpInside
    -0.10
    )application
    -0.08
    ConverterFactory
    -0.08
    .habbo
    -0.08
    _exempt
    -0.07
    )frame
    -0.07
    \Migration
    -0.07
    SystemService
    -0.07
    )did
    -0.07
     crave
    -0.07
    POSITIVE LOGITS
     “âĢ¦
    0.13
    ...↵↵↵
    0.13
    âĢ¦.↵↵
    0.13
    âĢ¦"
    0.12
    âĢ¦..
    0.11
    !↵↵↵↵
    0.11
    .Currency
    0.11
    ,âĢ¦
    0.11
     âĢ¦.
    0.11
    .Serial
    0.10
    Activations Density 18.161%

    No Known Activations