© 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. 119241
    Prev
    Next
    INDEX
    Explanations

    boolean expressions and status checks in 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
    imizer
    -0.07
    ivÄĽ
    -0.07
    ivec
    -0.07
    lik
    -0.06
    enez
    -0.06
    aln
    -0.06
    ırak
    -0.06
    pectives
    -0.06
     subur
    -0.06
    olina
    -0.06
    POSITIVE LOGITS
     Is
    0.08
     bool
    0.07
    .contains
    0.07
    .has
    0.07
     isinstance
    0.07
    æĺ¯åIJ¦
    0.07
    :Boolean
    0.07
    .is
    0.07
     onCreateOptionsMenu
    0.07
    .IsMatch
    0.07
    Activations Density 0.218%

    No Known Activations