© 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. 59588
    Prev
    Next
    INDEX
    Explanations

    symbols and structural elements related to instructions or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãģĦãĤĦ
    -0.07
    gent
    -0.07
    anova
    -0.07
    å²³
    -0.07
    enheim
    -0.07
     Flake
    -0.07
    _marshall
    -0.07
    кÑĥл
    -0.06
    //{{
    -0.06
    lint
    -0.06
    POSITIVE LOGITS
    ir
    0.07
    bern
    0.06
    ifen
    0.06
     Ler
    0.06
     completed
    0.06
    umber
    0.06
    ird
    0.06
    ute
    0.06
    isch
    0.06
     dissip
    0.06
    Activations Density 0.001%

    No Known Activations