© 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. 38654
    Prev
    Next
    INDEX
    Explanations

    BufReader and Vec definitions

    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
     Shoe
    -0.10
     sel
    -0.10
     bells
    -0.09
     brute
    -0.09
     nat
    -0.09
     plugs
    -0.09
     bell
    -0.09
    .FileReader
    -0.09
     Bell
    -0.09
     brutal
    -0.08
    POSITIVE LOGITS
     stream
    0.27
     Stream
    0.21
    stream
    0.21
     streams
    0.18
    Stream
    0.18
    .stream
    0.17
    \tstream
    0.16
    (stream
    0.15
     io
    0.15
    _stream
    0.14
    Activations Density 0.062%

    No Known Activations