© 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. 88338
    Prev
    Next
    INDEX
    Explanations

    sentences that express agreement or affirmation

    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
     therefore
    -0.09
     thus
    -0.08
     ÐŁÐ¾ÑįÑĤомÑĥ
    -0.08
     Therefore
    -0.08
    Therefore
    -0.07
    Thus
    -0.07
     Thus
    -0.07
     Accordingly
    -0.07
     Consequently
    -0.06
    ï¼ĮåĽłæѤ
    -0.06
    POSITIVE LOGITS
    ----</
    0.08
    ---</
    0.07
    zeit
    0.07
    fila
    0.07
    steller
    0.07
    .Expression
    0.07
    êu
    0.07
    lio
    0.07
    rew
    0.06
     misunder
    0.06
    Activations Density 0.038%

    No Known Activations