© 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. 44707
    Prev
    Next
    INDEX
    Explanations

    severed and beaten

    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
    çĹħ
    -0.10
    nero
    -0.10
     Wich
    -0.10
     sweaty
    -0.10
     disease
    -0.10
     ï¾ŀ
    -0.10
    ovies
    -0.09
    benh
    -0.09
     illness
    -0.09
    æļ´
    -0.09
    POSITIVE LOGITS
    conc
    0.23
     Conc
    0.22
     conc
    0.20
     concussion
    0.19
     cuts
    0.18
     spr
    0.18
     cont
    0.16
     minor
    0.15
     Minor
    0.14
     ribs
    0.14
    Activations Density 0.038%

    No Known Activations