© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41064
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and experimental procedures

    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
    /xhtml
    -0.07
    ully
    -0.06
    <?,
    -0.06
    ibly
    -0.06
    illy
    -0.06
    Interop
    -0.06
    ariant
    -0.06
    enso
    -0.06
    ften
    -0.06
    trs
    -0.06
    POSITIVE LOGITS
     dur
    0.07
     célib
    0.07
     pri
    0.06
     res
    0.06
    eler
    0.06
    anton
    0.06
    .Void
    0.06
    lon
    0.06
    datatype
    0.06
    126
    0.06
    Activations Density 0.055%

    No Known Activations