© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5715
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to various topics, including places, people, and brands

    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
    Äįet
    -0.09
    _Context
    -0.09
    #echo
    -0.09
    #ad
    -0.08
    кол
    -0.08
     addCriterion
    -0.08
    .sessions
    -0.08
    _________________↵↵
    -0.08
    оÑĢож
    -0.08
    имÑĥ
    -0.08
    POSITIVE LOGITS
    âĢ¦
    0.07
     meaning
    0.07
     (
    0.07
     means
    0.07
    ..
    0.07
     pronounced
    0.06
     =
    0.06
     stands
    0.06
     indeed
    0.06
     *
    0.06
    Activations Density 0.034%

    No Known Activations