© 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 EvalsExportsAPI 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. 56093
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and structure in programming code

    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
     per
    -0.07
     perform
    -0.06
    iers
    -0.06
    ictor
    -0.06
     rapid
    -0.06
    iggers
    -0.06
    roup
    -0.06
    zos
    -0.06
    ete
    -0.05
    odon
    -0.05
    POSITIVE LOGITS
    меÑĤÑĮ
    0.09
     {}.
    0.07
    iller
    0.06
     shouldn
    0.06
    kah
    0.06
    çĿ
    0.06
    Pont
    0.06
    amt
    0.06
    {}.
    0.06
    æĸŃ
    0.06
    Activations Density 0.002%

    No Known Activations