© 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 EvalsExportsinterp-engineNEWAPI 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. 5409
    Prev
    Next
    INDEX
    Explanations

    references to the mathematical term "pi"

    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
    edir
    -0.09
    achuset
    -0.07
    oftware
    -0.07
    press
    -0.07
    onse
    -0.07
    aper
    -0.07
    stinence
    -0.07
    rias
    -0.07
    ersh
    -0.07
    PCS
    -0.07
    POSITIVE LOGITS
    LOT
    0.09
    aget
    0.07
    elle
    0.07
    ÂŁ
    0.07
    LOTS
    0.07
    _INLINE
    0.06
    angs
    0.06
     Lah
    0.06
    wald
    0.06
    omer
    0.06
    Activations Density 0.010%

    No Known Activations