Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65279
    Prev
    Next
    INDEX
    Explanations

    running large models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caldwell
    -0.10
     Lump
    -0.09
     Tall
    -0.09
     Kinh
    -0.09
     ste
    -0.08
     prototype
    -0.08
     Lexer
    -0.08
     multinational
    -0.08
    era
    -0.08
     trailer
    -0.08
    POSITIVE LOGITS
     models
    0.15
     model
    0.13
    模åŀĭ
    0.12
     Models
    0.12
    _models
    0.12
     weights
    0.12
    -model
    0.11
    .setModel
    0.11
    models
    0.11
    _model
    0.11
    Activations Density 0.169%

    No Known Activations