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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5711
    Prev
    Next
    INDEX
    Explanations

    references to health-related statistics and topics

    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
    ibold
    -0.08
    .Îķ
    -0.08
    udur
    -0.08
     bì
    -0.08
    оваÑĢ
    -0.07
    746
    -0.07
    tah
    -0.07
     ÑĤÑĢан
    -0.07
    oleÄį
    -0.07
    uil
    -0.07
    POSITIVE LOGITS
     recently
    0.07
     ever
    0.07
     recent
    0.07
     any
    0.07
    any
    0.06
    recent
    0.06
     Any
    0.06
     last
    0.06
     Ever
    0.06
     lately
    0.06
    Activations Density 0.014%

    No Known Activations