© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    genres of movies and their 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
    ÑĴ
    -0.07
    Ñıб
    -0.07
    _blank
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    楼
    -0.07
    .learn
    -0.07
    umm
    -0.06
    лаÑĤи
    -0.06
    okt
    -0.06
    _validate
    -0.06
    POSITIVE LOGITS
     Vernon
    0.06
    elman
    0.06
    δι
    0.06
    æľĿ
    0.06
     Darling
    0.05
     disjoint
    0.05
    arium
    0.05
    ição
    0.05
    627
    0.05
    adian
    0.05
    Activations Density 0.004%

    No Known Activations