© 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. 79721
    Prev
    Next
    INDEX
    Explanations

    key concepts related to media content and its impact on events or decisions

    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
    kerja
    -0.07
    bara
    -0.07
     eser
    -0.07
    ÄĽtÅ¡
    -0.07
    Ïĩο
    -0.07
    áo
    -0.07
    cher
    -0.07
    abad
    -0.07
    Bu
    -0.07
    bu
    -0.07
    POSITIVE LOGITS
     versus
    0.07
     recent
    0.07
     vs
    0.07
     recently
    0.07
     instead
    0.06
     compared
    0.06
     Maur
    0.06
     allegedly
    0.06
    wb
    0.06
     alleged
    0.06
    Activations Density 0.036%

    No Known Activations