© 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. 104579
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to complex dimensions

    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
    idla
    -0.08
    uze
    -0.08
    auss
    -0.08
    ZY
    -0.07
    ÐŁÐļ
    -0.07
    lÃŃ
    -0.07
     çľ
    -0.07
    ANDOM
    -0.07
    ceph
    -0.07
    esy
    -0.07
    POSITIVE LOGITS
    iac
    0.07
     Pou
    0.06
     Jones
    0.06
    ional
    0.06
    ister
    0.05
    isan
    0.05
    xp
    0.05
    usive
    0.05
    iren
    0.05
     rel
    0.05
    Activations Density 0.077%

    No Known Activations