© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64718
    Prev
    Next
    INDEX
    Explanations

    not typical, not known, not major

    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
    Negative Logits
     possibly
    -0.17
    possibly
    -0.14
     Possibly
    -0.13
    åı¯èĥ½
    -0.13
     potentially
    -0.12
     possible
    -0.12
     unprecedented
    -0.11
     возможно
    -0.10
    Possible
    -0.10
    possible
    -0.10
    POSITIVE LOGITS
     major
    0.25
     immediate
    0.21
     apprec
    0.17
     immediately
    0.17
    major
    0.17
     significant
    0.16
    æľīä»Ģä¹Ī
    0.14
     necessarily
    0.14
     signific
    0.13
    -major
    0.13
    Activations Density 0.107%

    No Known Activations