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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44950
    Prev
    Next
    INDEX
    Explanations

    model incorrectly predicts

    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
     true
    -0.12
     yes
    -0.11
    =YES
    -0.10
     âľĵ
    -0.10
    (true
    -0.10
    Unavailable
    -0.10
    fty
    -0.09
    =true
    -0.09
     similarly
    -0.09
    581
    -0.09
    POSITIVE LOGITS
    åIJ¦
    0.12
     ê·¸ëłĩ
    0.12
     NOT
    0.12
    hta
    0.12
     naopak
    0.11
     falsehood
    0.11
     either
    0.11
    NegativeButton
    0.11
     False
    0.11
     FALSE
    0.10
    Activations Density 0.068%

    No Known Activations