© 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. 40717
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of characters and actors in movies

    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
     erotico
    -0.08
    ottes
    -0.07
    oger
    -0.07
    agnost
    -0.07
    utivo
    -0.06
    ære
    -0.06
    antity
    -0.06
    uder
    -0.06
    hazi
    -0.06
    earer
    -0.06
    POSITIVE LOGITS
     cast
    0.09
     actors
    0.08
    饰
    0.08
     Ledger
    0.07
     actor
    0.07
     acting
    0.07
     casting
    0.07
    飾
    0.06
     actresses
    0.06
     casts
    0.06
    Activations Density 0.097%

    No Known Activations