© 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. 15-LLAMASCOPE-RES-131K
    11. 89410
    Prev
    Next
    INDEX
    Explanations

    code snippets or structures related to user interface elements and configuration settings

    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
     mop
    -0.06
    _CTL
    -0.06
    prog
    -0.06
    ↵
    -0.06
     Ngh
    -0.06
    zer
    -0.06
    ÑĤал
    -0.06
    -0.06
    ubern
    -0.06
    syn
    -0.06
    POSITIVE LOGITS
    apus
    0.07
    aukee
    0.07
    éĽ¢
    0.06
    ahren
    0.06
     Gardner
    0.06
    ipse
    0.06
     illustr
    0.06
     Wilkinson
    0.06
     ActiveForm
    0.06
    iones
    0.06
    Activations Density 0.008%

    No Known Activations