© 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. 44780
    Prev
    Next
    INDEX
    Explanations

    dictionary keys and entries

    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
     cris
    -0.10
     subs
    -0.10
     overd
    -0.09
    oland
    -0.09
     consec
    -0.09
     Pist
    -0.09
     Craw
    -0.09
    avad
    -0.09
    .datasource
    -0.09
    ivate
    -0.09
    POSITIVE LOGITS
     keys
    0.43
     Keys
    0.37
    keys
    0.36
    Keys
    0.34
    .keys
    0.32
    _keys
    0.31
    -keys
    0.26
    \tkeys
    0.24
    (keys
    0.22
     key
    0.21
    Activations Density 0.068%

    No Known Activations