© 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. 27855
    Prev
    Next
    INDEX
    Explanations

    elements of code structures or syntax

    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
     servisi
    -0.08
    obre
    -0.07
    éł
    -0.07
    fortawesome
    -0.07
    nob
    -0.07
     discrepan
    -0.07
    ebe
    -0.07
    ç¸
    -0.07
    нки
    -0.07
     */,
    -0.07
    POSITIVE LOGITS
     Crosby
    0.07
    488
    0.07
     void
    0.06
    uling
    0.06
    elson
    0.06
     inline
    0.06
     friend
    0.06
     Sid
    0.06
    NN
    0.06
     Hem
    0.05
    Activations Density 0.002%

    No Known Activations