© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4061
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly focusing on syntax elements like semicolons and numbers

    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
     Rank
    -0.07
    iffin
    -0.07
    wchar
    -0.07
    rank
    -0.06
    ypi
    -0.06
     damer
    -0.06
    bourg
    -0.06
    863
    -0.06
    olut
    -0.06
     Graham
    -0.06
    POSITIVE LOGITS
     Vu
    0.07
     Dah
    0.07
    ophil
    0.06
    sey
    0.06
    óz
    0.06
    ighton
    0.06
    igid
    0.06
    ısından
    0.06
    _tel
    0.06
     Nico
    0.06
    Activations Density 0.001%

    No Known Activations