© 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. 127735
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and logical 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
    .Modules
    -0.07
    !!!!↵↵
    -0.07
    æİĽ
    -0.07
    à¸ļà¸ģ
    -0.07
    581
    -0.07
     VÄĽ
    -0.07
    //{{
    -0.07
    æĶ¶å½ķ
    -0.07
    ứng
    -0.07
    ानà¤ķ
    -0.07
    POSITIVE LOGITS
     third
    0.16
     Third
    0.14
    -third
    0.13
    third
    0.13
    Third
    0.12
     THIRD
    0.12
    第ä¸ī
    0.11
     第ä¸ī
    0.11
     ÑĤÑĢеÑĤÑĮ
    0.11
    _third
    0.11
    Activations Density 0.137%

    No Known Activations