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. 31-LLAMASCOPE-RES-131K
    6. 44028
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to astronomy and astrophysics

    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
     resto
    -0.07
     vitam
    -0.07
    ظÙħ
    -0.07
    еÑĤÑĥ
    -0.07
    ->___
    -0.07
    axon
    -0.06
    má
    -0.06
    .PNG
    -0.06
    undy
    -0.06
     Fixes
    -0.06
    POSITIVE LOGITS
     detection
    0.08
     distribution
    0.07
     presence
    0.07
     fraction
    0.07
     measured
    0.07
     put
    0.07
     inferred
    0.07
     pa
    0.07
     observed
    0.07
     dear
    0.07
    Activations Density 0.088%

    No Known Activations