© 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. 17432
    Prev
    Next
    INDEX
    Explanations

    can plus ability

    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
    ãĥ¥
    -0.11
    ivo
    -0.09
     Fah
    -0.09
    tems
    -0.09
     Ches
    -0.09
    YD
    -0.08
     Logistic
    -0.08
    geist
    -0.08
    ata
    -0.08
    oty
    -0.08
    POSITIVE LOGITS
    't
    0.22
    ’;t
    0.21
     easily
    0.21
    /w
    0.17
     Easily
    0.16
     potentially
    0.16
    /do
    0.13
    'T
    0.13
     feas
    0.13
    ’;T
    0.13
    Activations Density 0.100%

    No Known Activations