© 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. 61520
    Prev
    Next
    INDEX
    Explanations

    specific circumstances and how

    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
     Mim
    -0.10
    eker
    -0.09
    /Dk
    -0.09
    zier
    -0.09
    apot
    -0.08
    678
    -0.08
    sta
    -0.08
    ColumnInfo
    -0.08
     QLatin
    -0.08
    517
    -0.08
    POSITIVE LOGITS
     how
    0.17
     details
    0.17
     extent
    0.16
     manner
    0.16
     circumstances
    0.16
     degree
    0.15
     specific
    0.15
    åħ·ä½ĵ
    0.15
     implementation
    0.15
     exact
    0.15
    Activations Density 0.053%

    No Known Activations