© 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. 95531
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to programming and data structures

    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
    istrovstvÃŃ
    -0.11
    enu
    -0.10
     maybe
    -0.09
     mga
    -0.08
     meaningful
    -0.07
    /down
    -0.07
     طرÙĬÙĤ
    -0.07
    ixin
    -0.07
    aterno
    -0.07
    asn
    -0.07
    POSITIVE LOGITS
     Madness
    0.14
    ificent
    0.10
    intosh
    0.10
    hattan
    0.10
    angelo
    0.09
     Mondays
    0.09
    hammad
    0.09
    istrates
    0.09
    ellan
    0.09
    gomery
    0.09
    Activations Density 2.906%

    No Known Activations