© 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. 76108
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating degrees or comparisons

    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
    asel
    -0.08
    .Extension
    -0.07
    бÑĥд
    -0.07
    eyJ
    -0.07
    Ñīин
    -0.07
    lug
    -0.07
    оÑĢдин
    -0.07
    íĭ±
    -0.07
    tgl
    -0.07
    à¸Ńà¸Ļà¸Ķ
    -0.07
    POSITIVE LOGITS
     nil
    0.08
     ours
    0.08
     theirs
    0.08
     yours
    0.07
    okrat
    0.07
    нÑı
    0.06
    HS
    0.06
    nil
    0.06
    Nil
    0.06
     Nil
    0.06
    Activations Density 0.037%

    No Known Activations