© 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. 34154
    Prev
    Next
    INDEX
    Explanations

    listing followed by detail

    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
     ìŀĪê³ł
    -0.14
    íĸĪê³ł
    -0.12
    ãģĮãģĤãĤĬ
    -0.10
    ë¥´ê³ł
    -0.10
    ë¦¬ê³ł
    -0.10
    AndUpdate
    -0.09
    åĩºãģĹ
    -0.09
    AndPassword
    -0.08
    eyh
    -0.08
    pivot
    -0.08
    POSITIVE LOGITS
    ï¿
    0.12
     serta
    0.10
     ultimately
    0.10
     etc
    0.09
    ult
    0.09
    '||
    0.08
    IJëĭ¤
    0.08
     respectively
    0.08
    ,,,,,,,,
    0.08
    OF
    0.08
    Activations Density 0.158%

    No Known Activations