© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24233
    Prev
    Next
    INDEX
    Explanations

    mentioning specific words or phrases

    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
    ean
    -0.08
    oden
    -0.08
    habit
    -0.08
    /Add
    -0.08
     Consort
    -0.08
     pendant
    -0.08
    ursive
    -0.08
     fetisch
    -0.08
    VERSE
    -0.08
     Defined
    -0.07
    POSITIVE LOGITS
     words
    0.16
     mention
    0.16
     keywords
    0.14
     contains
    0.14
     tone
    0.14
     phrase
    0.14
     phrases
    0.13
    Keywords
    0.13
     contain
    0.12
    contains
    0.12
    Activations Density 0.135%

    No Known Activations