© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127178
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in achievements or notable identities

    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
    šk
    -0.08
    aju
    -0.07
    addock
    -0.06
     Ø®ÙĦ
    -0.06
    Filed
    -0.06
    argent
    -0.06
     anew
    -0.06
    ibus
    -0.06
    ertz
    -0.06
    ritten
    -0.06
    POSITIVE LOGITS
    дÑĥ
    0.07
    setCurrent
    0.07
     Compression
    0.06
    ojis
    0.06
    shi
    0.06
    estre
    0.06
     Metrics
    0.06
    æĿIJ
    0.06
     dilation
    0.06
     Buen
    0.06
    Activations Density 0.005%

    No Known Activations