© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93643
    Prev
    Next
    INDEX
    Explanations

    terms related to programming structures and their attributes

    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
    WindowTitle
    -0.07
    mey
    -0.06
     Duch
    -0.06
    isas
    -0.06
    .documentation
    -0.06
    áv
    -0.06
    isman
    -0.06
    Sampler
    -0.05
    Î
    -0.05
    .hwp
    -0.05
    POSITIVE LOGITS
    vron
    0.07
    UNUSED
    0.07
    aeda
    0.07
    stral
    0.07
    æ±
    0.07
     Lau
    0.06
    ully
    0.06
    onne
    0.06
    062
    0.06
    ovalo
    0.06
    Activations Density 0.092%

    No Known Activations