© 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. 32106
    Prev
    Next
    INDEX
    Explanations

    skills, ingredients, and topics

    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
    542
    -0.09
    Cerrar
    -0.09
     Stern
    -0.09
    736
    -0.08
    UNUSED
    -0.08
    ÑĢÑĥÑģ
    -0.08
    locs
    -0.08
     ï¾ļ
    -0.08
     Demp
    -0.08
    _ctxt
    -0.08
    POSITIVE LOGITS
     quality
    0.11
     aspect
    0.09
    âĪ
    0.09
     score
    0.09
     Verd
    0.08
     |
    0.08
    -related
    0.08
     aspects
    0.08
    SEN
    0.08
    ::/
    0.08
    Activations Density 0.027%

    No Known Activations