© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 58002
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions in 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
     Fre
    -0.06
    _REPEAT
    -0.06
    imestone
    -0.06
     tuá»ķi
    -0.06
    _charset
    -0.05
     Css
    -0.05
     adolescence
    -0.05
     stones
    -0.05
    dap
    -0.05
    غاÙĨ
    -0.05
    POSITIVE LOGITS
     JSON
    0.14
     json
    0.13
    json
    0.12
    .JSON
    0.12
    JSON
    0.12
    .json
    0.11
    =json
    0.11
    .Json
    0.11
    .JSONObject
    0.11
    _JSON
    0.10
    Activations Density 0.081%

    No Known Activations