© 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
    5. 50-RESID-POST-GF
    7. 37923
    Prev
    Next
    INDEX
    Explanations

    transfer learning and adaptation

    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
    iks
    -0.10
    oute
    -0.09
     pet
    -0.09
     Lara
    -0.09
    HW
    -0.09
     Bat
    -0.09
     cl
    -0.08
    .groupby
    -0.08
    amin
    -0.08
     Grat
    -0.08
    POSITIVE LOGITS
     transfer
    0.30
     Transfer
    0.29
    Transfer
    0.26
    transfer
    0.26
     transferred
    0.23
     transfers
    0.22
    _transfer
    0.22
    -transfer
    0.22
    TRANSFER
    0.21
    .Transfer
    0.20
    Activations Density 0.049%

    No Known Activations