© 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. 38201
    Prev
    Next
    INDEX
    Explanations

    optimistic despite, dark humor, positive energy

    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
    uno
    -0.10
     Beng
    -0.09
    ahoo
    -0.09
     disadv
    -0.09
    EMPLARY
    -0.09
    ******/
    -0.08
    oller
    -0.08
    ãĥ³ãĥĦ
    -0.08
     sober
    -0.08
    .scalablytyped
    -0.08
    POSITIVE LOGITS
    optim
    0.38
     Optim
    0.36
     optim
    0.36
     опÑĤим
    0.33
     optimistic
    0.32
     optimism
    0.30
    Opt
    0.28
    .optim
    0.26
     glass
    0.24
     positive
    0.23
    Activations Density 0.128%

    No Known Activations