© 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. 107818
    Prev
    Next
    INDEX
    Explanations

    instances of random number generation and matrix-related functions

    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
    standing
    -0.08
    ниÑĩеÑģ
    -0.07
    avanaugh
    -0.07
    sak
    -0.07
    edl
    -0.07
    stood
    -0.07
    orthy
    -0.06
     kapit
    -0.06
    èĬĿ
    -0.06
    .MixedReality
    -0.06
    POSITIVE LOGITS
     shape
    0.08
     Shape
    0.06
    uga
    0.06
     shaped
    0.06
    _unicode
    0.06
    shape
    0.06
    (shape
    0.06
     Tea
    0.06
    ache
    0.06
    iors
    0.06
    Activations Density 0.009%

    No Known Activations