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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34547
    Prev
    Next
    INDEX
    Explanations

    polymaths and their ideas

    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
     Hussein
    -0.13
     mythology
    -0.11
    185
    -0.11
     mim
    -0.10
     Myth
    -0.10
     myth
    -0.10
     Ludwig
    -0.10
     Phú
    -0.09
     archae
    -0.09
    186
    -0.09
    POSITIVE LOGITS
     treat
    0.20
     al
    0.16
     polym
    0.15
     Treat
    0.15
     medieval
    0.14
    Alchemy
    0.12
     Leonardo
    0.12
    rega
    0.11
     Kit
    0.11
     Medieval
    0.11
    Activations Density 0.063%

    No Known Activations