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. 31-LLAMASCOPE-RES-131K
    6. 43839
    Prev
    Next
    INDEX
    Explanations

    elements related to character performance and dramatic intensity

    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
    assen
    -0.06
     fetisch
    -0.06
    isure
    -0.06
    nych
    -0.06
     Erotische
    -0.06
    Wunused
    -0.06
    icensed
    -0.06
    xED
    -0.06
    è£ķ
    -0.05
     Geile
    -0.05
    POSITIVE LOGITS
     protagonist
    0.10
     hero
    0.10
     Hero
    0.10
     conflict
    0.10
     Conflict
    0.09
     Act
    0.09
     antagonist
    0.09
     Plot
    0.09
     plot
    0.08
     resolution
    0.08
    Activations Density 0.005%

    No Known Activations