© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125856
    Prev
    Next
    INDEX
    Explanations

    references to movie directors and their works

    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
    874
    -0.07
    opak
    -0.07
    POSITE
    -0.06
    åħ¬å¼ı
    -0.06
    Ïĩο
    -0.06
    _shadow
    -0.06
    .ht
    -0.06
    ULA
    -0.06
    UPI
    -0.06
     Gret
    -0.06
    POSITIVE LOGITS
    çĽ£çĿ£
    0.12
     director
    0.11
     ê°IJëıħ
    0.11
     directed
    0.10
    director
    0.10
    dir
    0.09
     directors
    0.09
    -direct
    0.09
     Director
    0.09
    Directed
    0.09
    Activations Density 0.037%

    No Known Activations