© 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. 55346
    Prev
    Next
    INDEX
    Explanations

    issues related to event handling in a web application

    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
     merkezi
    -0.07
    çĽ
    -0.07
    trys
    -0.07
    inka
    -0.07
    -fetch
    -0.07
    eron
    -0.07
    óż
    -0.07
     Sın
    -0.07
    åıĸãĤĬ
    -0.07
    æī
    -0.06
    POSITIVE LOGITS
    apid
    0.07
    utton
    0.07
     initial
    0.06
     initially
    0.06
    ito
    0.06
    apo
    0.06
    oj
    0.06
    ÑĢоÑĪ
    0.06
    807
    0.05
     Hayes
    0.05
    Activations Density 0.010%

    No Known Activations