© 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. 15-LLAMASCOPE-RES-131K
    6. 90583
    Prev
    Next
    INDEX
    Explanations

    unexpected symbols or formatting in the text

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

    Text containing references to data types, formatting symbols, or specialized notation in various computer languages, food menus, or structured 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
    aland
    -0.07
    icro
    -0.06
    ¼
    -0.06
    ered
    -0.06
     Kostenlose
    -0.06
    /or
    -0.06
    lee
    -0.06
    |
    -0.06
    eren
    -0.06
    of
    -0.06
    POSITIVE LOGITS
    .bunifuFlatButton
    0.09
    _exempt
    0.08
    .Guna
    0.08
    redients
    0.08
    ancellable
    0.08
    /GPL
    0.08
    isphere
    0.08
    ainless
    0.07
    _subplot
    0.07
    â̦↵↵↵
    0.07
    Activations Density 0.040%

    No Known Activations