© 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. 38148
    Prev
    Next
    INDEX
    Explanations

    ML model prediction generate

    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
     Bayesian
    -0.10
     Pascal
    -0.10
     relics
    -0.10
     Arithmetic
    -0.10
    Measurement
    -0.09
    pard
    -0.09
    pie
    -0.09
    ihu
    -0.09
     Worm
    -0.09
    measurement
    -0.09
    POSITIVE LOGITS
     model
    0.18
     machine
    0.17
     models
    0.16
     Machine
    0.15
     ML
    0.13
     binary
    0.13
     variables
    0.12
    模åŀĭ
    0.12
    Machine
    0.12
    (machine
    0.12
    Activations Density 0.157%

    No Known Activations