© 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. 129815
    Prev
    Next
    INDEX
    Explanations

    references to scholarly citations and academic discussions

    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
    parator
    -0.07
    insk
    -0.07
    redient
    -0.07
     Fres
    -0.07
    alama
    -0.07
    azzo
    -0.07
    ç»ıçIJĨ
    -0.07
    _ASSUME
    -0.07
    аÑĢам
    -0.07
    loh
    -0.07
    POSITIVE LOGITS
    eping
    0.07
     historian
    0.06
    æº
    0.06
     soci
    0.06
     disc
    0.06
     tertiary
    0.06
     Sus
    0.06
    663
    0.06
     Eden
    0.05
     Mark
    0.05
    Activations Density 0.044%

    No Known Activations