© 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. 128085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "subscribe" related to newsletters or updates

    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
     Morr
    -0.07
    ouz
    -0.07
    chet
    -0.07
    rie
    -0.06
    rade
    -0.06
    stre
    -0.06
    çıł
    -0.06
     constexpr
    -0.06
    rist
    -0.06
    à¸Ļาà¸Ļ
    -0.06
    POSITIVE LOGITS
     fur
    0.08
    .unsubscribe
    0.07
    ToArray
    0.07
    .FieldName
    0.07
    utable
    0.07
    anness
    0.07
    itar
    0.07
     newsp
    0.06
    /******/
    0.06
    edd
    0.06
    Activations Density 0.003%

    No Known Activations