© 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. 47253
    Prev
    Next
    INDEX
    Explanations

    parallel, perpendicular, cross

    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
     triangular
    -0.12
     clockwise
    -0.12
     diagon
    -0.11
     protr
    -0.10
    yg
    -0.10
     Armed
    -0.09
     Ferd
    -0.09
     axial
    -0.09
     borne
    -0.09
     Rab
    -0.09
    POSITIVE LOGITS
     parallel
    0.32
    parallel
    0.29
     trans
    0.29
     Parallel
    0.28
    Parallel
    0.28
    _parallel
    0.24
     cross
    0.23
    pendicular
    0.22
     Cross
    0.19
     ob
    0.19
    Activations Density 0.128%

    No Known Activations