© 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. 129737
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant effort or commitment

    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
    itty
    -0.07
    emiz
    -0.06
    nu
    -0.06
    UTO
    -0.06
     bomb
    -0.05
    bomb
    -0.05
    ech
    -0.05
     Vital
    -0.05
     laps
    -0.05
     brute
    -0.05
    POSITIVE LOGITS
    ÑĢаÑĤно
    0.08
    ublic
    0.07
    pta
    0.07
    лÑĸв
    0.07
    odu
    0.07
    mlink
    0.07
    issen
    0.07
    ompiler
    0.07
    ','','
    0.07
     effort
    0.07
    Activations Density 0.004%

    No Known Activations