© 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. 15-LLAMASCOPE-RES-131K
    11. 61937
    Prev
    Next
    INDEX
    Explanations

    referenced works and their respective authors or publishers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A closing parenthesis that typically follows a year date in bibliographic citations, particularly in gaming catalog entries from the early 1980s.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    amura
    -0.07
    моÑĢ
    -0.07
    (disposing
    -0.07
    üz
    -0.07
    ÌĢ
    -0.06
    kish
    -0.06
    itudes
    -0.06
     ÅŁÃ¶yle
    -0.06
    åĹ
    -0.06
     Opport
    -0.06
    POSITIVE LOGITS
    eci
    0.08
    elin
    0.07
    ega
    0.06
    ecera
    0.06
    isode
    0.06
    ventus
    0.06
    /Resources
    0.06
    ilver
    0.06
    ouser
    0.06
    oodle
    0.06
    Activations Density 0.155%

    No Known Activations