© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29732
    Prev
    Next
    INDEX
    Explanations

    descriptions of experiences related to acting and performance in theater and film

    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
     Crosby
    -0.07
    oyal
    -0.07
    lobal
    -0.06
    ject
    -0.06
    brane
    -0.06
    iae
    -0.06
    /books
    -0.06
    .Reporting
    -0.06
    czy
    -0.06
    azon
    -0.06
    POSITIVE LOGITS
     Production
    0.09
     production
    0.09
    production
    0.08
    Production
    0.08
    _production
    0.08
     shoot
    0.07
     Pocket
    0.07
     shorts
    0.07
     productions
    0.07
     project
    0.07
    Activations Density 0.079%

    No Known Activations