© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33505
    Prev
    Next
    INDEX
    Explanations

    path, one leading

    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
    utto
    -0.12
     MSS
    -0.09
     Readonly
    -0.09
     performed
    -0.09
    .intellij
    -0.08
    airs
    -0.08
     limits
    -0.08
     tail
    -0.08
     wings
    -0.08
    onet
    -0.08
    POSITIVE LOGITS
     path
    0.18
     tro
    0.15
    Taken
    0.15
     leading
    0.15
     chosen
    0.14
     taken
    0.14
     Taken
    0.14
    tro
    0.14
     dẫn
    0.14
    =path
    0.13
    Activations Density 0.065%

    No Known Activations