© 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. 58268
    Prev
    Next
    INDEX
    Explanations

    geographic information and references to locations

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

    Punctuation and grammatical connector words in structured document metadata, particularly in geologic map citations where commas separate location elements and "by" or "and" connect author names or geographic entities.

    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
    ÑĥÑĩа
    -0.07
     Hamm
    -0.07
    ÃĹ↵↵
    -0.06
     <!--[
    -0.06
     doby
    -0.06
     ç¢
    -0.06
    formance
    -0.06
    Ãły
    -0.06
     PyTuple
    -0.06
     веÑĢеÑģ
    -0.06
    POSITIVE LOGITS
     L
    0.13
     ल
    0.11
     ÙĦ
    0.11
     ÐĽ
    0.11
    $L
    0.11
    ÂłL
    0.11
    _l
    0.10
     l
    0.10
    .L
    0.10
     ׾
    0.10
    Activations Density 0.732%

    No Known Activations