© 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. 76809
    Prev
    Next
    INDEX
    Explanations

    references to recent events or timeframes

    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
     later
    -0.07
    िà¤
    -0.07
     Lau
    -0.06
    o
    -0.06
     many
    -0.06
     other
    -0.06
     eventually
    -0.06
    á»ijt
    -0.06
     not
    -0.06
    ateria
    -0.06
    POSITIVE LOGITS
    hower
    0.07
    mente
    0.07
    :border
    0.07
    ngle
    0.07
    ecome
    0.06
    utilus
    0.06
    çļĦæĺ¯
    0.06
    liš
    0.06
    emodel
    0.06
    tring
    0.06
    Activations Density 0.004%

    No Known Activations