© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38662
    Prev
    Next
    INDEX
    Explanations

    create and install

    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
    .createServer
    -0.12
     create
    -0.11
     Create
    -0.11
    _CREATE
    -0.11
    /create
    -0.11
     creates
    -0.10
    _create
    -0.10
     creation
    -0.10
    Create
    -0.10
    create
    -0.10
    POSITIVE LOGITS
     filled
    0.12
     fill
    0.12
     populate
    0.11
     populated
    0.11
    .populate
    0.11
     Fill
    0.11
    .Fill
    0.11
     à¤ĩसम
    0.10
     filling
    0.10
    Filled
    0.10
    Activations Density 0.102%

    No Known Activations