© 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. 28639
    Prev
    Next
    INDEX
    Explanations

    expressions and activities related to family and outdoor enjoyment

    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
    airy
    -0.07
    adt
    -0.07
    itol
    -0.06
    mey
    -0.06
    kker
    -0.06
    umblr
    -0.06
     ÑĥÑħод
    -0.06
    adle
    -0.06
    mil
    -0.06
    opo
    -0.06
    POSITIVE LOGITS
    ÄĽr
    0.06
     endwhile
    0.06
     any
    0.06
    quia
    0.06
    eldo
    0.06
    istrovstvÃŃ
    0.06
    :Any
    0.06
     whichever
    0.06
     whenever
    0.06
     Bak
    0.06
    Activations Density 0.031%

    No Known Activations