© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36393
    Prev
    Next
    INDEX
    Explanations

    for the ... to begin/be/show

    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
    ohan
    -0.12
    æĪĴ
    -0.10
    508
    -0.09
    647
    -0.09
    寸
    -0.09
     Fang
    -0.09
     unarmed
    -0.09
    881
    -0.09
    buster
    -0.09
    ohen
    -0.09
    POSITIVE LOGITS
     merc
    0.18
     escape
    0.18
     Escape
    0.16
     numb
    0.15
     rid
    0.14
     end
    0.14
    escape
    0.14
    éĢĥ
    0.14
     ESC
    0.13
     away
    0.13
    Activations Density 0.040%

    No Known Activations