© 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. 5-LLAMASCOPE-RES-131K
    11. 125411
    Prev
    Next
    INDEX
    Explanations

    references to elite or top-tier performance in various contexts

    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
    burger
    -0.08
    zas
    -0.06
    _KP
    -0.06
    obe
    -0.06
    mp
    -0.06
    burg
    -0.06
    zial
    -0.06
    ney
    -0.06
    oser
    -0.06
     YES
    -0.06
    POSITIVE LOGITS
    каÑģ
    0.07
    Unload
    0.07
    ertools
    0.06
    ummings
    0.06
    461
    0.06
     subsidized
    0.06
    luet
    0.06
    abbr
    0.06
    leston
    0.06
    ExceptionHandler
    0.06
    Activations Density 0.003%

    No Known Activations