© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56285
    Prev
    Next
    INDEX
    Explanations

    hypothetical outcomes and possibilities

    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
     usually
    -0.10
    rite
    -0.10
     Sic
    -0.10
    aise
    -0.09
     sometimes
    -0.09
    äºĨ
    -0.08
     Stap
    -0.08
     can
    -0.08
     Claus
    -0.08
     prostit
    -0.08
    POSITIVE LOGITS
     kdyby
    0.17
     depending
    0.15
     could
    0.14
     if
    0.13
     Could
    0.13
     hypoth
    0.13
     hypothetical
    0.12
    depending
    0.12
     would
    0.12
    Could
    0.12
    Activations Density 0.266%

    No Known Activations