© 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. 128449
    Prev
    Next
    INDEX
    Explanations

    the word "You" and its variations, indicating a focus on addressing the reader directly

    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
    untas
    -0.07
    éric
    -0.07
    Ãłm
    -0.06
    aceous
    -0.06
    ynec
    -0.06
    doch
    -0.06
    ocate
    -0.06
    uppies
    -0.06
     Gür
    -0.06
    ób
    -0.06
    POSITIVE LOGITS
     can
    0.08
     may
    0.07
    ths
    0.07
     prompt
    0.06
    FullPath
    0.06
    may
    0.06
     Prompt
    0.06
    isman
    0.06
     also
    0.06
    thus
    0.06
    Activations Density 0.027%

    No Known Activations