© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93879
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the best of America or notable qualities associated with it

    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
    anse
    -0.07
    isper
    -0.07
    duk
    -0.07
    eyi
    -0.07
    cé
    -0.07
    alon
    -0.07
    etto
    -0.07
    дем
    -0.06
    igsaw
    -0.06
    _OBJC
    -0.06
    POSITIVE LOGITS
    este
    0.06
    amer
    0.06
    udden
    0.06
    ëĭ¥
    0.05
     breed
    0.05
    owing
    0.05
    haul
    0.05
    Ïģο
    0.05
    -eff
    0.05
     Breed
    0.05
    Activations Density 0.011%

    No Known Activations