Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5535
    Prev
    Next
    INDEX
    Explanations

    references to film directors and historical events concerning tragic incidents

    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
    AKER
    -0.06
    eken
    -0.06
    ulur
    -0.06
    ehen
    -0.06
    .slim
    -0.06
    _cpus
    -0.06
    éłĨ
    -0.06
    yük
    -0.06
    Warnings
    -0.06
    mour
    -0.06
    POSITIVE LOGITS
    ovny
    0.07
    entrant
    0.07
     knÃŃ
    0.07
    ĶåĽŀ
    0.06
    oni
    0.06
     Lew
    0.06
     LAP
    0.06
    afia
    0.06
     UCLA
    0.06
     Spiel
    0.06
    Activations Density 0.002%

    No Known Activations