© 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. 127239
    Prev
    Next
    INDEX
    Explanations

    instances of closing braces or handlings of pairs in formatting or coding

    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
    s
    -0.08
    ÑĬ
    -0.08
    ãģĤ
    -0.07
    	↵	↵	↵
    -0.07
    ÑĦоÑĢ
    -0.07
    work
    -0.07
    YW
    -0.07
    fall
    -0.07
     Tender
    -0.07
    ainty
    -0.07
    POSITIVE LOGITS
    er
    0.12
    e
    0.12
    ÙĬ
    0.09
    a
    0.09
    ity
    0.09
    ãĥ¥
    0.08
    o
    0.08
    eil
    0.08
    erus
    0.08
    erer
    0.08
    Activations Density 0.086%

    No Known Activations