© 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. 82813
    Prev
    Next
    INDEX
    Explanations

    sentiments and expressions of personal opinion about entertainment

    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
    òi
    -0.08
    _VIRTUAL
    -0.07
    ensors
    -0.07
    ÑĢеб
    -0.07
    ữ
    -0.07
    μή
    -0.06
    ennie
    -0.06
    alse
    -0.06
    رض
    -0.06
    urvey
    -0.06
    POSITIVE LOGITS
     watching
    0.07
     íĮ¬
    0.07
     him
    0.07
     watch
    0.06
    дÑĢ
    0.06
     그를
    0.06
     idol
    0.06
     fandom
    0.06
     Watching
    0.06
     onun
    0.06
    Activations Density 0.039%

    No Known Activations