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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59951
    Prev
    Next
    INDEX
    Explanations

    references to unique contributions or qualities related to people or entities

    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
    opp
    -0.06
    ourg
    -0.06
    tail
    -0.06
     occas
    -0.06
    burgh
    -0.06
     tail
    -0.06
    ocide
    -0.06
    occasion
    -0.06
    sto
    -0.06
    оÑĢон
    -0.06
    POSITIVE LOGITS
    utters
    0.08
    Äįe
    0.07
     MOST
    0.06
    ptime
    0.06
    utter
    0.06
    ypy
    0.06
    652
    0.06
    plib
    0.06
    bservice
    0.06
     Sang
    0.06
    Activations Density 0.045%

    No Known Activations