© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71146
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    наÑħ
    -0.07
    iveau
    -0.07
    ette
    -0.06
    ienes
    -0.06
     SplashScreen
    -0.06
    ÑģÑĤоÑĢиÑı
    -0.06
    inee
    -0.06
    nb
    -0.06
    uzzi
    -0.06
    QueryParam
    -0.06
    POSITIVE LOGITS
     bidding
    0.08
     bid
    0.08
     auctions
    0.08
    Bid
    0.08
     bids
    0.07
     auction
    0.07
     Bid
    0.07
     Auction
    0.07
    ç§Ģ
    0.07
    Win
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.