Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29416
    Prev
    Next
    INDEX
    Explanations

    references to artistic inspiration and creativity

    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
     immediately
    -0.06
     pitch
    -0.06
     offerings
    -0.06
     k
    -0.06
     tent
    -0.06
     Courtesy
    -0.06
     up
    -0.06
     kon
    -0.06
     zero
    -0.05
     potential
    -0.05
    POSITIVE LOGITS
    à¸Ķย
    0.09
    $MESS
    0.09
    eydi
    0.09
     stol
    0.09
    eprom
    0.08
     rodin
    0.08
    æ°¸ä¹ħ
    0.08
    ï¼ĮåŃĺäºİ
    0.07
    tones
    0.07
    aget
    0.07
    Activations Density 0.019%

    No Known Activations