© 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. 83427
    Prev
    Next
    INDEX
    Explanations

    formatted data structures or code snippets

    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
    ppe
    -0.07
    idis
    -0.07
    Ãłnh
    -0.06
    анов
    -0.06
    warf
    -0.06
    agnost
    -0.06
    !↵↵↵↵↵↵
    -0.06
     offsetof
    -0.06
     hesab
    -0.06
    pen
    -0.06
    POSITIVE LOGITS
    llib
    0.06
     Desired
    0.06
     corresponding
    0.06
     ingin
    0.06
    entine
    0.06
    712
    0.06
    Want
    0.06
     want
    0.06
    auer
    0.06
    æĥ³è¦ģ
    0.06
    Activations Density 0.019%

    No Known Activations