© 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. 56023
    Prev
    Next
    INDEX
    Explanations

    the presence of formulas or mathematical notation

    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
    ju
    -0.07
    eso
    -0.06
    erc
    -0.06
    indows
    -0.06
    ices
    -0.06
     tv
    -0.05
     deed
    -0.05
    ales
    -0.05
    üle
    -0.05
    ustin
    -0.05
    POSITIVE LOGITS
    aģı
    0.07
    _backend
    0.07
    ëĵľë¦¬
    0.07
    #ac
    0.07
    ิà¹Ģศษ
    0.07
    orque
    0.07
    tÃŃ
    0.07
    itti
    0.07
    ClientRect
    0.07
     McGr
    0.07
    Activations Density 0.001%

    No Known Activations