© 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. 93864
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and scientific terminology

    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
    raç
    -0.07
    ounge
    -0.07
    oola
    -0.07
    eko
    -0.06
    agas
    -0.06
    sis
    -0.06
    utation
    -0.06
    igan
    -0.06
    uya
    -0.06
    anela
    -0.06
    POSITIVE LOGITS
    ayer
    0.08
    strcasecmp
    0.06
    AYER
    0.06
     fieldValue
    0.06
    ollen
    0.06
    itin
    0.06
    sel
    0.06
    atten
    0.06
    Layers
    0.06
     mist
    0.06
    Activations Density 0.003%

    No Known Activations