© 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. 93819
    Prev
    Next
    INDEX
    Explanations

    statements about code functionality and equivalence in programming

    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
    elles
    -0.07
    lev
    -0.07
    δÏģα
    -0.06
     lev
    -0.06
    .Payload
    -0.06
    opoly
    -0.06
    622
    -0.06
     Òij
    -0.06
    ecz
    -0.06
    ocache
    -0.06
    POSITIVE LOGITS
     equivalent
    0.07
    Ú
    0.06
     correct
    0.06
     correctly
    0.06
    ucch
    0.06
     sequence
    0.06
     dilig
    0.06
    æĪIJç«ĭ
    0.06
     equivalence
    0.06
     BUG
    0.06
    Activations Density 0.023%

    No Known Activations