© 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. 92410
    Prev
    Next
    INDEX
    Explanations

    elements of code or programming 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
    anie
    -0.06
    924
    -0.06
     urge
    -0.06
    apel
    -0.05
     pred
    -0.05
    gle
    -0.05
     LC
    -0.05
    anza
    -0.05
     rush
    -0.05
    ž
    -0.05
    POSITIVE LOGITS
    ispers
    0.09
    ãĥªãĤ«
    0.08
    #ad
    0.08
    .gf
    0.08
    оба
    0.07
    uldu
    0.07
     минÑĥ
    0.07
    @student
    0.07
     gesch
    0.07
     ãĢĪ
    0.07
    Activations Density 0.020%

    No Known Activations