© 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. 28369
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and syntax

    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
    Ŀ¼
    -0.07
    ä¸ĸ
    -0.07
    ¿IJ
    -0.06
     اÙĦرÙħزÙĬØ©
    -0.06
    ¯¼
    -0.06
    ÑĥÑĩа
    -0.06
    ems
    -0.06
     æķħ
    -0.06
    PictureBox
    -0.06
    ¯u
    -0.06
    POSITIVE LOGITS
    enco
    0.08
    allo
    0.07
    lsa
    0.06
    Encode
    0.06
    orne
    0.06
    ffa
    0.06
    ochen
    0.06
    haf
    0.06
     dog
    0.06
    /REC
    0.06
    Activations Density 0.029%

    No Known Activations