© 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. 44704
    Prev
    Next
    INDEX
    Explanations

    yourself and others

    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
     ãħĩãħĩ
    -0.10
     dp
    -0.09
     쪽ì§Ģ
    -0.08
    Ñľ
    -0.08
     opportun
    -0.08
     EXEMPLARY
    -0.07
    ฯ
    -0.07
    ,eg
    -0.07
    dük
    -0.07
    edly
    -0.07
    POSITIVE LOGITS
    zar
    0.09
    ãģ§ãģĤãĤĬ
    0.08
    ,proto
    0.08
    Ìģ
    0.07
     snapchat
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
     //~
    0.07
     _______,
    0.07
    ãĢģ​
    0.07
     #__
    0.07
    Activations Density 0.001%

    No Known Activations