© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83137
    Prev
    Next
    INDEX
    Explanations

    keywords related to asynchronous programming and synchronization concepts

    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
     風
    -0.07
    hoot
    -0.07
    746
    -0.06
    OOT
    -0.06
    wig
    -0.06
    oard
    -0.06
    临
    -0.06
     Heard
    -0.06
    LastError
    -0.06
    ész
    -0.06
    POSITIVE LOGITS
     void
    0.09
    urer
    0.07
    dal
    0.07
    urtle
    0.06
    void
    0.06
    ÑĨÑı
    0.06
     boolean
    0.06
    oba
    0.06
    dialogs
    0.06
    esters
    0.06
    Activations Density 0.001%

    No Known Activations