© 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. 16873
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts or syntax, particularly related to functions and expressions

    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
    oje
    -0.08
    bower
    -0.08
    avage
    -0.07
    redient
    -0.07
    bearer
    -0.07
    /null
    -0.07
    é¢Ŀ
    -0.07
     kino
    -0.07
    -UA
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
     posted
    0.06
     surprising
    0.06
     attached
    0.06
     Deutsch
    0.06
    633
    0.06
     qu
    0.06
    emey
    0.05
     play
    0.05
     sealed
    0.05
    arent
    0.05
    Activations Density 0.030%

    No Known Activations