© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    amount or proportion of action

    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
     slightest
    -0.09
    istrovstvÃŃ
    -0.09
    hos
    -0.09
    afone
    -0.09
     jedem
    -0.08
    ESH
    -0.08
    qli
    -0.08
    elleicht
    -0.08
     Ùħتعدد
    -0.08
    AtA
    -0.08
    POSITIVE LOGITS
     much
    0.47
     majority
    0.45
     most
    0.40
    much
    0.35
     vÄĽtÅ¡
    0.32
     Much
    0.32
     part
    0.30
    Much
    0.30
     ëĮĢë¶Ģë¶Ħ
    0.30
     Majority
    0.29
    Activations Density 0.219%

    No Known Activations