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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16950
    Prev
    Next
    INDEX
    Explanations

    references to influential figures in the film industry and their contributions

    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
    leigh
    -0.07
    ETA
    -0.07
     sucker
    -0.07
    fang
    -0.07
     Aires
    -0.06
    semblies
    -0.06
    Äįer
    -0.06
     dern
    -0.06
     ÏĩÏī
    -0.06
    Ïģκ
    -0.06
    POSITIVE LOGITS
     era
    0.09
     golden
    0.09
     Golden
    0.08
     period
    0.08
     boom
    0.08
    golden
    0.07
    Golden
    0.07
     Era
    0.07
    ystack
    0.06
     Boom
    0.06
    Activations Density 0.084%

    No Known Activations