© 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. 86495
    Prev
    Next
    INDEX
    Explanations

    technical language related to signal processing and system performance

    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
     Compression
    -0.07
    emoc
    -0.07
    arde
    -0.07
     Preservation
    -0.07
     puzzles
    -0.06
    673
    -0.06
    iasco
    -0.06
    æĻ´
    -0.06
     наÑĤ
    -0.06
     dash
    -0.06
    POSITIVE LOGITS
    alıdır
    0.07
    они
    0.06
    Ñĩно
    0.06
     algorithm
    0.06
    eya
    0.06
     Mode
    0.06
     Infinity
    0.06
     Wil
    0.06
    OPLE
    0.06
    ylvania
    0.06
    Activations Density 0.093%

    No Known Activations