© 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. 123578
    Prev
    Next
    INDEX
    Explanations

    exclamatory remarks and calls to action related to media consumption, particularly music or radio

    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
    ovich
    -0.07
    lick
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    ittel
    -0.07
    redients
    -0.06
    اÙħÛĮÙĨ
    -0.06
    olest
    -0.06
    addons
    -0.06
    \Annotation
    -0.06
    wins
    -0.06
    POSITIVE LOGITS
    rag
    0.06
     listening
    0.06
    .listen
    0.06
     ëĵ£
    0.06
    sta
    0.06
    ReadStream
    0.06
    zig
    0.06
     NPR
    0.06
     tracks
    0.05
     cert
    0.05
    Activations Density 0.001%

    No Known Activations