© 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. 9-LLAMASCOPE-RES-131K
    11. 96834
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to APIs or technical updates

    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
    eced
    -0.07
    ervals
    -0.06
    ee
    -0.06
    Ø¡
    -0.06
    jest
    -0.06
    sein
    -0.06
    iste
    -0.06
    iae
    -0.06
    iese
    -0.06
    reh
    -0.06
    POSITIVE LOGITS
    --+
    0.06
    Å¡il
    0.06
    ULER
    0.06
    .misc
    0.06
    /Area
    0.06
    antas
    0.06
     Foley
    0.06
    ÃŃnu
    0.06
    122
    0.06
    mand
    0.06
    Activations Density 0.000%

    No Known Activations