© 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. 48886
    Prev
    Next
    INDEX
    Explanations

    placeholders for names and variables

    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
     latter
    -0.10
    .Companion
    -0.09
    ëĵł
    -0.08
     ucwords
    -0.08
    uden
    -0.08
    anzi
    -0.08
    urry
    -0.08
    ditor
    -0.08
     cousin
    -0.08
     ÑģÑĤан
    -0.08
    POSITIVE LOGITS
     numerator
    0.12
    å·¦åı³
    0.11
    âijł
    0.10
    ","");\n
    0.09
     both
    0.09
     halves
    0.09
     Late
    0.09
    both
    0.09
    ãĤĬãģ¨
    0.09
    两个
    0.08
    Activations Density 0.199%

    No Known Activations