© 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. 55491
    Prev
    Next
    INDEX
    Explanations

    patterns of numbers or formatting indicative of technical data or statistical information

    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
     foss
    -0.07
     bomb
    -0.07
    ifndef
    -0.06
    lique
    -0.06
    opia
    -0.06
    htag
    -0.06
    svp
    -0.06
    omain
    -0.06
    undi
    -0.06
    ges
    -0.06
    POSITIVE LOGITS
    &r
    0.07
    pain
    0.07
    %B
    0.07
     Freed
    0.07
    :NO
    0.06
    zik
    0.06
     Pain
    0.06
     Drum
    0.06
    812
    0.06
    å¹ķ
    0.06
    Activations Density 0.001%

    No Known Activations