© 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. 125118
    Prev
    Next
    INDEX
    Explanations

    JavaScript function declarations and assignments

    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
    eydi
    -0.08
    HAS
    -0.07
    NSE
    -0.07
    ãĥ¼ãĥ©
    -0.07
    áv
    -0.06
    squ
    -0.06
    ãİ¡
    -0.06
    hea
    -0.06
    aus
    -0.06
    eland
    -0.06
    POSITIVE LOGITS
     function
    0.08
    function
    0.07
     async
    0.06
    =lambda
    0.06
     Ur
    0.06
    719
    0.06
    async
    0.06
    orth
    0.06
    utos
    0.06
    589
    0.06
    Activations Density 0.008%

    No Known Activations