© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127988
    Prev
    Next
    INDEX
    Explanations

    programming syntax and specific code structures

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

    Special formatting commands or markdown elements in technical documents, often indicating formatting instructions for text, code blocks, comments, or bibliography styles in LaTeX or HTML documents.

    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
    isnan
    -0.08
    اÙĦÙĬا
    -0.07
    ÑĢаÑĤно
    -0.07
    ----------------------------------------------------------------------↵
    -0.06
    .contentType
    -0.06
    utf
    -0.06
    /fontawesome
    -0.06
    _DECL
    -0.06
    foreground
    -0.06
    bero
    -0.06
    POSITIVE LOGITS
    ibal
    0.07
    cete
    0.07
    VEC
    0.07
    pare
    0.06
    mÃŃt
    0.06
    ppo
    0.06
     Rudd
    0.06
     vest
    0.06
    elow
    0.06
    μί
    0.06
    Activations Density 0.035%

    No Known Activations