© 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. 125282
    Prev
    Next
    INDEX
    Explanations

    references to film success and notable movie attributes

    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
    uce
    -0.07
    uers
    -0.06
     fasc
    -0.06
    ÑĦоÑĢми
    -0.06
     Giang
    -0.06
    ornings
    -0.06
    _ASC
    -0.06
    uke
    -0.06
    ierrez
    -0.06
     Readers
    -0.06
    POSITIVE LOGITS
    plot
    0.09
     movie
    0.09
    movie
    0.08
     plot
    0.08
    film
    0.07
     ê°IJëıħ
    0.07
    Plot
    0.07
     film
    0.07
    HD
    0.07
    ofilm
    0.07
    Activations Density 0.024%

    No Known Activations