© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or emergence from a situation

    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
    u
    -0.08
    973
    -0.07
    oon
    -0.06
    odash
    -0.06
    713
    -0.06
    obra
    -0.06
    kip
    -0.06
    descriptor
    -0.06
    566
    -0.06
    dots
    -0.06
    POSITIVE LOGITS
     Clarkson
    0.07
     involved
    0.07
     Mess
    0.06
    Rol
    0.06
    -gnu
    0.06
     mess
    0.06
     rid
    0.06
     Jed
    0.06
    tings
    0.06
     NSUInteger
    0.06
    Activations Density 0.010%

    No Known Activations