© 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. 44411
    Prev
    Next
    INDEX
    Explanations

    numbers following decimal points

    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
    _,,
    -0.10
     hij
    -0.09
     eas
    -0.09
    auen
    -0.09
    ukkit
    -0.09
     gu
    -0.09
    们
    -0.09
    ''"
    -0.09
    èIJ¬
    -0.09
    âī¦
    -0.08
    POSITIVE LOGITS
    00
    0.16
    000
    0.12
    oo
    0.11
    0
    0.11
    AT
    0.10
    Origin
    0.10
    Ind
    0.10
    Us
    0.09
    upt
    0.09
    5
    0.09
    Activations Density 0.081%

    No Known Activations