© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90211
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mechanics and adjustments

    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
     dục
    -0.07
    æĽ¿
    -0.07
    λÎŃ
    -0.07
    scaling
    -0.06
    burg
    -0.06
     dem
    -0.06
     tou
    -0.06
    ÃŃch
    -0.06
     رÙħز
    -0.06
    iants
    -0.06
    POSITIVE LOGITS
    Breadcrumb
    0.06
    =device
    0.06
    POSITE
    0.06
     sett
    0.06
    itore
    0.06
     Fletcher
    0.06
     toler
    0.06
     Hüs
    0.06
     correct
    0.05
     Governors
    0.05
    Activations Density 0.066%

    No Known Activations