© 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. 17-LLAMASCOPE-RES-131K
    11. 40044
    Prev
    Next
    INDEX
    Explanations

    numerical values and phrases related to quantities and limitations

    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
    utenberg
    -0.08
    jen
    -0.08
    ustos
    -0.07
     Schneider
    -0.07
    fat
    -0.07
     Shops
    -0.07
    issions
    -0.06
    jez
    -0.06
    umar
    -0.06
    stad
    -0.06
    POSITIVE LOGITS
     quantity
    0.12
    Quantity
    0.10
     Quantity
    0.10
     quantities
    0.09
    quantity
    0.09
    _quantity
    0.08
    .Quantity
    0.07
    (quantity
    0.07
    .quantity
    0.07
    Qty
    0.07
    Activations Density 0.003%

    No Known Activations