© 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. 129918
    Prev
    Next
    INDEX
    Explanations

    numerical values representing years

    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
    moth
    -0.07
    annon
    -0.07
    336
    -0.07
    ature
    -0.07
    enaire
    -0.07
    aira
    -0.07
    uten
    -0.07
    inou
    -0.07
    gua
    -0.06
     esk
    -0.06
    POSITIVE LOGITS
    os
    0.07
     Orchard
    0.07
    оÑĢоÑĤ
    0.06
    λιά
    0.06
    sus
    0.06
    los
    0.06
    wang
    0.06
    logger
    0.06
     Kelly
    0.06
    sonian
    0.06
    Activations Density 0.036%

    No Known Activations