© 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. 56324
    Prev
    Next
    INDEX
    Explanations

    references to educational courses and their organization

    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
    ileo
    -0.07
    iÄĻ
    -0.07
    loff
    -0.07
    icket
    -0.07
    inx
    -0.07
    797
    -0.06
     hyp
    -0.06
    åªĴ
    -0.06
     Hayes
    -0.06
     TICK
    -0.06
    POSITIVE LOGITS
     card
    0.08
    âĻł
    0.07
     Card
    0.06
    -card
    0.06
     cards
    0.06
    itaire
    0.06
    table
    0.06
    .appspot
    0.06
     Strategic
    0.06
     Fle
    0.06
    Activations Density 0.001%

    No Known Activations