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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117753
    Prev
    Next
    INDEX
    Explanations

    punctuation and connective words that suggest contrast or additional information

    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
    quez
    -0.07
    ogo
    -0.06
    огод
    -0.06
     causa
    -0.06
    aign
    -0.06
    \TestCase
    -0.06
    field
    -0.06
     ordered
    -0.06
    ennen
    -0.06
    _cpp
    -0.06
    POSITIVE LOGITS
     prelim
    0.07
    ãģ¾ãģļ
    0.07
    åı¯èĥ½æĢ§
    0.07
    oplan
    0.07
     idea
    0.07
     city
    0.07
     potentially
    0.06
     potential
    0.06
     pitch
    0.06
     uten
    0.06
    Activations Density 0.001%

    No Known Activations