© 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. 38378
    Prev
    Next
    INDEX
    Explanations

    measurement units for physical properties

    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
    e
    -0.12
    y
    -0.11
    a
    -0.10
    yyyy
    -0.10
    b
    -0.10
    ãĥ¥
    -0.10
    yyy
    -0.09
    ÑģÑĮ
    -0.09
    agrid
    -0.09
    edList
    -0.09
    POSITIVE LOGITS
    eters
    0.17
    ètres
    0.17
    trs
    0.16
    illion
    0.14
    ÙĬÙĦاد
    0.14
    xmm
    0.13
    'er
    0.13
    elsius
    0.13
    iles
    0.12
    ilion
    0.12
    Activations Density 0.072%

    No Known Activations