© 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. 64603
    Prev
    Next
    INDEX
    Explanations

    couch or sofa

    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
    ç¥Ń
    -0.11
     McGr
    -0.11
     bedside
    -0.10
     dresser
    -0.10
     bedding
    -0.10
     onOptionsItemSelected
    -0.09
     conc
    -0.09
    .metamodel
    -0.09
     bedtime
    -0.09
    hower
    -0.09
    POSITIVE LOGITS
     couch
    0.26
     Couch
    0.25
     arm
    0.21
     living
    0.21
     sofa
    0.20
     TV
    0.19
     Living
    0.18
     Sofa
    0.17
     television
    0.16
    Living
    0.15
    Activations Density 0.051%

    No Known Activations