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

    Neuronpedia

    Jacobian LensNEW
    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. 40460
    Prev
    Next
    INDEX
    Explanations

    references to film characteristics and production elements

    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
    itar
    -0.07
    anger
    -0.06
    agle
    -0.06
    upo
    -0.06
    unger
    -0.06
    нож
    -0.06
    ati
    -0.06
     Hermes
    -0.06
    aine
    -0.06
     Seymour
    -0.06
    POSITIVE LOGITS
    film
    0.10
     film
    0.10
     films
    0.10
     movie
    0.09
     movies
    0.09
     ÏĦαιν
    0.08
     projects
    0.08
    movie
    0.08
     pelÃŃcula
    0.08
    films
    0.08
    Activations Density 0.046%

    No Known Activations