© 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. 87871
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical processes and materials

    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
     mur
    -0.06
     susceptibility
    -0.06
     versus
    -0.06
    éĢģæĸĻ
    -0.05
     kari
    -0.05
     potentially
    -0.05
     vers
    -0.05
    رÛĮÙħ
    -0.05
     tor
    -0.05
    ennis
    -0.05
    POSITIVE LOGITS
    uto
    0.07
    ElementsBy
    0.07
    elles
    0.07
    žit
    0.07
    LOAT
    0.07
    atır
    0.07
     forming
    0.07
    ä½ľçĶ¨
    0.07
    ätz
    0.07
    uro
    0.07
    Activations Density 0.016%

    No Known Activations