© 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. 28597
    Prev
    Next
    INDEX
    Explanations

    references to achievements and rankings in competitions

    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
    au
    -0.08
    aur
    -0.07
    alsa
    -0.06
    icha
    -0.06
    Rows
    -0.06
    ellig
    -0.06
    713
    -0.06
    addle
    -0.06
    Shown
    -0.06
    $GLOBALS
    -0.06
    POSITIVE LOGITS
     while
    0.08
     thanks
    0.07
     vac
    0.07
     whereas
    0.07
    while
    0.07
    indre
    0.07
     tro
    0.06
     ìĿ´ë²Ī
    0.06
     mentre
    0.06
     yesterday
    0.06
    Activations Density 0.018%

    No Known Activations