© 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. 10739
    Prev
    Next
    INDEX
    Explanations

    fourth, four

    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
    oth
    -0.10
    isten
    -0.09
     hex
    -0.09
    ãĢģä¸ī
    -0.09
    aal
    -0.09
     à¤Ńà¤Ĺ
    -0.08
    ipt
    -0.08
     nond
    -0.08
    est
    -0.08
     sext
    -0.08
    POSITIVE LOGITS
     fourth
    0.28
    ç¬¬åĽĽ
    0.23
     Fourth
    0.22
    Fourth
    0.22
     ÑĩеÑĤвеÑĢ
    0.18
     FOUR
    0.18
     forth
    0.17
     fours
    0.16
     Äįtvrt
    0.16
     four
    0.15
    Activations Density 0.183%

    No Known Activations