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. 76589
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical contexts

    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
    ir
    -0.06
    -headed
    -0.06
    s
    -0.06
     in
    -0.05
     I
    -0.05
    [
    -0.05
    urer
    -0.05
     min
    -0.05
    tures
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    ToLocal
    0.09
    ÄĽÅ¾
    0.08
    æĸĻçĦ¡æĸĻ
    0.08
    Äł
    0.08
    ControlItem
    0.08
    loquent
    0.08
     gá»ijc
    0.08
    gren
    0.08
    ofire
    0.08
    ÃĹ</
    0.08
    Activations Density 0.028%

    No Known Activations