© 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 EvalsExportsinterp-engineNEWAPI 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. 2090
    Prev
    Next
    INDEX
    Explanations

    occurrences of technical or automated comments within code

    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
    Äįet
    -0.07
    fait
    -0.07
    trie
    -0.07
    ãģıãĤī
    -0.07
    anos
    -0.07
    iek
    -0.07
    indi
    -0.07
    comed
    -0.06
    arro
    -0.06
    λλι
    -0.06
    POSITIVE LOGITS
     Twin
    0.07
    ypad
    0.07
    545
    0.06
    uido
    0.06
     Richardson
    0.06
    Accessibility
    0.06
    ë¡ł
    0.06
    rick
    0.06
     doGet
    0.06
    ÐĺТ
    0.06
    Activations Density 0.001%

    No Known Activations