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

    Neuronpedia

    Jacobian LensNEW
    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. 87424
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structure in coding languages

    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
    ÙĪÙĦÙĩ
    -0.07
     íĭ
    -0.07
    ude
    -0.06
    argo
    -0.06
    à¤Ĥर
    -0.06
    :maj
    -0.06
    /full
    -0.06
    arget
    -0.06
    ANGLES
    -0.06
    /stretch
    -0.06
    POSITIVE LOGITS
    ABL
    0.06
    dül
    0.06
     Kem
    0.06
     Ster
    0.06
     alike
    0.05
    оÑĢоÑĤ
    0.05
     Binder
    0.05
    หาร
    0.05
     Apparel
    0.05
    ابر
    0.05
    Activations Density 0.056%

    No Known Activations