© 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. 38338
    Prev
    Next
    INDEX
    Explanations

    was written

    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
     Oaks
    -0.11
     Chap
    -0.10
    achen
    -0.10
    ãĥ«ãĥĪ
    -0.10
    uster
    -0.09
    akin
    -0.09
     丶
    -0.09
    447
    -0.09
    671
    -0.08
    /--
    -0.08
    POSITIVE LOGITS
     çĶ±
    0.18
    çĶ±
    0.18
     zosta
    0.15
     was
    0.15
     fue
    0.13
     foi
    0.12
     were
    0.12
     fueron
    0.12
     wurde
    0.12
    å½Ĵ
    0.12
    Activations Density 0.178%

    No Known Activations