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. 71177
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or skepticism regarding vaccination statistics

    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
    .appspot
    -0.10
    ÄĽtÅ¡
    -0.09
     addslashes
    -0.09
    iska
    -0.08
    znam
    -0.08
     swingers
    -0.08
    racat
    -0.08
     (*((
    -0.08
    pgsql
    -0.08
    OPSIS
    -0.08
    POSITIVE LOGITS
     
    0.09
     (
    0.08
    ,
    0.08
     [
    0.07
     American
    0.07
    ↵
    0.07
     President
    0.07
    .
    0.06
     leadership
    0.06
     "
    0.06
    Activations Density 0.713%

    No Known Activations