© 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. 38095
    Prev
    Next
    INDEX
    Explanations

    textual features

    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
    éĹ
    -0.09
    udi
    -0.09
    _wf
    -0.09
    operand
    -0.09
    ãĥĸãĥ©
    -0.09
    interop
    -0.09
    åİĤ
    -0.09
    ainty
    -0.09
     Hunt
    -0.08
    Disposable
    -0.08
    POSITIVE LOGITS
     Dudley
    0.11
     sal
    0.11
     query
    0.11
     aday
    0.10
     ground
    0.10
     aligned
    0.10
    etur
    0.10
     halluc
    0.10
     observed
    0.10
    obs
    0.10
    Activations Density 0.174%

    No Known Activations