© 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. 87999
    Prev
    Next
    INDEX
    Explanations

    phrases containing questions or opinions related to thoughts and feelings

    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
     Reasons
    -0.07
    ifu
    -0.07
     reasons
    -0.07
    -many
    -0.06
     itself
    -0.06
    ä½ķ
    -0.06
    nego
    -0.06
    rei
    -0.06
    reason
    -0.06
    849
    -0.06
    POSITIVE LOGITS
    /use
    0.08
    еле
    0.07
    obar
    0.07
    olang
    0.07
    cha
    0.07
    aby
    0.06
    abled
    0.06
    apat
    0.06
    pty
    0.06
     suger
    0.06
    Activations Density 0.008%

    No Known Activations