© 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. 38007
    Prev
    Next
    INDEX
    Explanations

    comma separated

    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
     rational
    -0.10
     Rational
    -0.10
     Nested
    -0.10
    ress
    -0.09
     Prefix
    -0.09
    åŃĹ
    -0.08
    anni
    -0.08
    _nested
    -0.08
    ï¾
    -0.08
     namedtuple
    -0.08
    POSITIVE LOGITS
     comma
    0.39
    comma
    0.34
     coma
    0.24
     commas
    0.22
    coma
    0.21
     Com
    0.19
     separated
    0.19
    Com
    0.18
    éĢ
    0.18
    Separated
    0.18
    Activations Density 0.267%

    No Known Activations