© 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. 20152
    Prev
    Next
    INDEX
    Explanations

    consequences or subsequent actions

    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
    romo
    -0.09
     ance
    -0.09
    omo
    -0.08
    statt
    -0.08
     dusk
    -0.08
    离
    -0.08
    cape
    -0.08
    strlen
    -0.08
    ahn
    -0.08
    'gc
    -0.08
    POSITIVE LOGITS
     then
    0.32
     thì
    0.29
    then
    0.29
    åĪĻ
    0.29
    åīĩ
    0.27
     maka
    0.27
     entonces
    0.25
    ï¼ĮåĪĻ
    0.22
     alors
    0.22
     Then
    0.21
    Activations Density 0.036%

    No Known Activations