© 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. 1914
    Prev
    Next
    INDEX
    Explanations

    activities and processes related to editing and refining content or artwork

    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
    roje
    -0.07
     vej
    -0.06
    laughter
    -0.06
    å¥ı
    -0.06
    flip
    -0.06
    .partial
    -0.06
    ÛĮÙĨÚ¯
    -0.06
    progress
    -0.06
    ëŁ¼
    -0.06
    زر
    -0.06
    POSITIVE LOGITS
     minor
    0.09
    minor
    0.07
     slightly
    0.07
     some
    0.07
    igar
    0.07
    ateg
    0.07
    orgia
    0.06
     slight
    0.06
    lux
    0.06
     wherever
    0.06
    Activations Density 0.030%

    No Known Activations