© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 82858
    Prev
    Next
    INDEX
    Explanations

    numerical and mathematical expressions

    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
    fet
    -0.07
    ман
    -0.07
    finger
    -0.06
     nouve
    -0.06
    /Instruction
    -0.06
     gén
    -0.06
    ساÙĨÛĮ
    -0.06
    ¢
    -0.06
    ¸
    -0.06
    UnderTest
    -0.06
    POSITIVE LOGITS
    719
    0.06
    .Embed
    0.06
     spos
    0.06
    iday
    0.06
     Bunny
    0.06
     receipt
    0.06
     cop
    0.06
    awy
    0.06
     Extras
    0.06
    ModelProperty
    0.06
    Activations Density 0.045%

    No Known Activations