© 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. 62622
    Prev
    Next
    INDEX
    Explanations

    continuation and word count

    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
    ort
    -0.09
    "
    -0.09
     whe
    -0.08
     Khal
    -0.08
     Norm
    -0.08
     Phelps
    -0.08
    ActiveSheet
    -0.08
    '
    -0.08
     imper
    -0.08
    442
    -0.08
    POSITIVE LOGITS
     continued
    0.16
     continue
    0.14
     continuation
    0.14
    continued
    0.12
    Continue
    0.12
     continuar
    0.12
    ç¶ļ
    0.12
    继ç»Ń
    0.11
     continues
    0.11
     пÑĢодолж
    0.11
    Activations Density 0.005%

    No Known Activations