© 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. 73027
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and mathematical operations

    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
    -vars
    -0.07
    emony
    -0.07
    suma
    -0.07
     zby
    -0.07
    alach
    -0.07
    Ìģt
    -0.07
    652
    -0.07
    bris
    -0.07
    visa
    -0.06
    rale
    -0.06
    POSITIVE LOGITS
    owski
    0.08
    itial
    0.07
     reverse
    0.06
     range
    0.06
     map
    0.06
     collection
    0.06
     pair
    0.06
     Trou
    0.06
    ([↵
    0.06
    467
    0.06
    Activations Density 0.010%

    No Known Activations