© 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 EvalsExportsinterp-engineNEWAPI 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. 17629
    Prev
    Next
    INDEX
    Explanations

    mentions of specific films and their performance in the movie industry

    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
    oda
    -0.08
    -b
    -0.07
    ali
    -0.07
    elli
    -0.06
    alaria
    -0.06
     Ful
    -0.06
    عر
    -0.05
    ï
    -0.05
    echa
    -0.05
     Gia
    -0.05
    POSITIVE LOGITS
    urat
    0.08
     addCriterion
    0.08
    ÙĪسÛĮ
    0.07
    gross
    0.07
     success
    0.07
     succès
    0.07
     sonu
    0.07
    Exited
    0.07
    cloth
    0.07
    $MESS
    0.07
    Activations Density 0.035%

    No Known Activations