© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    athletic season

    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
    reeNode
    -0.10
    abyrinth
    -0.09
     Hoy
    -0.09
    .LOGIN
    -0.09
    onia
    -0.08
     Tun
    -0.08
    usan
    -0.08
     quarterly
    -0.08
    adro
    -0.08
    íĭ
    -0.08
    POSITIVE LOGITS
     season
    0.46
     Ñģез
    0.36
     seasons
    0.30
     Season
    0.30
    season
    0.29
     sezon
    0.28
     temporada
    0.28
    -season
    0.27
    Season
    0.26
     saison
    0.24
    Activations Density 0.058%

    No Known Activations