© 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. 34218
    Prev
    Next
    INDEX
    Explanations

    after conjunctions and punctuation

    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
    .scalablytyped
    -0.10
     majority
    -0.10
    åĺī
    -0.09
     )\n\n\n\n\n\n\n\n
    -0.09
     weiber
    -0.09
    trak
    -0.09
    RuntimeObject
    -0.09
    Ä±ÅŁÄ±k
    -0.09
    pane
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
    POSITIVE LOGITS
     there
    0.12
     it
    0.11
     plenty
    0.09
     modulo
    0.09
     lord
    0.09
     any
    0.09
     Given
    0.09
     suffice
    0.09
     given
    0.09
     again
    0.09
    Activations Density 0.020%

    No Known Activations