© 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. 71240
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structure elements

    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
    loor
    -0.06
    anou
    -0.06
    ç´§
    -0.06
    à¤Łà¤ķ
    -0.06
     earth
    -0.06
    hana
    -0.06
    anko
    -0.05
    649
    -0.05
     invert
    -0.05
    _tokenize
    -0.05
    POSITIVE LOGITS
    innacle
    0.07
    SetActive
    0.07
     stom
    0.07
    /rss
    0.07
    linger
    0.07
     sider
    0.07
    ÅĻÃŃt
    0.07
     Ø¢ÛĮ
    0.06
     Briggs
    0.06
     signer
    0.06
    Activations Density 0.005%

    No Known Activations