© 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. 83461
    Prev
    Next
    INDEX
    Explanations

    titles and references associated with movies and entertainment

    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
    ê²łëĭ¤
    -0.05
     st
    -0.05
     io
    -0.05
     itself
    -0.05
     The
    -0.05
     appar
    -0.05
    еÑĢин
    -0.05
    åħĭæĸ¯
    -0.05
     pro
    -0.05
     It
    -0.05
    POSITIVE LOGITS
    geh
    0.10
    ragment
    0.08
    ftar
    0.08
    ouser
    0.08
    ieux
    0.08
    @nate
    0.08
    acher
    0.08
    rippling
    0.08
    feat
    0.08
    deaux
    0.08
    Activations Density 0.040%

    No Known Activations