© 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. 15-LLAMASCOPE-RES-131K
    11. 512
    Prev
    Next
    INDEX
    Explanations

    web links and references to external resources

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

    Navigation elements and URL components that serve as clickable links or interface elements on websites.

    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
    hev
    -0.06
    reo
    -0.06
    reff
    -0.06
    afd
    -0.06
    åŃĺäºİ
    -0.06
    ç³»
    -0.06
    bine
    -0.06
    mando
    -0.06
    GA
    -0.06
    ield
    -0.05
    POSITIVE LOGITS
    usty
    0.07
     confronted
    0.07
     editorial
    0.06
     Sawyer
    0.06
    ections
    0.06
    stown
    0.06
    à¥Ĥà¤ķ
    0.06
    ayım
    0.06
    igators
    0.06
    kate
    0.06
    Activations Density 0.047%

    No Known Activations