© 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. 5-LLAMASCOPE-RES-131K
    11. 126730
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their interactions related to metabolism

    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
    775
    -0.07
    oky
    -0.06
    £½
    -0.06
    OrElse
    -0.06
     Spin
    -0.06
    imiz
    -0.06
    873
    -0.06
    757
    -0.06
    851
    -0.06
    anio
    -0.06
    POSITIVE LOGITS
    izzo
    0.07
    _ros
    0.07
    iske
    0.07
    athe
    0.06
     moc
    0.06
    itone
    0.06
    æºĢ
    0.06
    ael
    0.06
    otron
    0.06
    jun
    0.06
    Activations Density 0.073%

    No Known Activations