© 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. 56135
    Prev
    Next
    INDEX
    Explanations

    lists connected by conjunctions

    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
     fetisch
    -0.10
    sans
    -0.08
    assin
    -0.08
    allon
    -0.08
     crossorigin
    -0.08
     ať
    -0.08
     erg
    -0.08
    aly
    -0.08
    anke
    -0.08
     mit
    -0.08
    POSITIVE LOGITS
    以åıĬ
    0.33
     serta
    0.29
    ï¼Į以åıĬ
    0.25
     oraz
    0.24
     respectively
    0.21
     ê·¸ë¦¬ê³ł
    0.21
     sowie
    0.20
     plus
    0.19
     ainsi
    0.18
     तथ
    0.17
    Activations Density 0.148%

    No Known Activations