© 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. 40303
    Prev
    Next
    INDEX
    Explanations

    elements related to character creation and customization in gaming

    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
    stad
    -0.09
    TARGET
    -0.08
    xt
    -0.08
     TARGET
    -0.08
    adge
    -0.08
    eyin
    -0.08
    inati
    -0.08
    egin
    -0.07
    LATED
    -0.07
    onte
    -0.07
    POSITIVE LOGITS
     characters
    0.10
     character
    0.10
     Characters
    0.09
     Character
    0.08
    characters
    0.07
    character
    0.07
     protagonist
    0.07
     karakter
    0.07
     chosen
    0.07
     protagonists
    0.07
    Activations Density 0.037%

    No Known Activations