© 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. 55328
    Prev
    Next
    INDEX
    Explanations

    elements indicating feedback or inquiries about content

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

    Punctuation and formatting symbols that structure or separate content in web comments, blog posts, and online forums.

    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
    anship
    -0.07
     Shutterstock
    -0.07
     WINAPI
    -0.07
    aepernick
    -0.07
    LError
    -0.06
    .experimental
    -0.06
    icide
    -0.06
    earer
    -0.06
    openh
    -0.06
    utherland
    -0.06
    POSITIVE LOGITS
    ral
    0.07
    elyn
    0.07
     STA
    0.07
    996
    0.07
    _RD
    0.07
    ãİ
    0.07
    engo
    0.07
     wr
    0.06
    vyk
    0.06
     Wald
    0.06
    Activations Density 0.038%

    No Known Activations