© 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. 129769
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures related to graphs

    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
    arker
    -0.07
     strerror
    -0.07
     taxonomy
    -0.07
    JsonValue
    -0.07
    cott
    -0.07
    semb
    -0.07
    /fl
    -0.06
    opus
    -0.06
     endregion
    -0.06
    decess
    -0.06
    POSITIVE LOGITS
    getMock
    0.07
    adesh
    0.07
    ecta
    0.06
    _singleton
    0.06
    ivé
    0.05
    inki
    0.05
     Team
    0.05
    ubu
    0.05
    Monad
    0.05
    jis
    0.05
    Activations Density 0.016%

    No Known Activations