© 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. 38581
    Prev
    Next
    INDEX
    Explanations

    gastric lung cancer treatments

    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
     clinically
    -0.11
     rein
    -0.09
     proto
    -0.09
    748
    -0.09
    ictim
    -0.09
     recipient
    -0.09
    _handles
    -0.09
    prot
    -0.09
    ict
    -0.09
     prot
    -0.08
    POSITIVE LOGITS
     refr
    0.21
     advanced
    0.16
     rel
    0.16
    advanced
    0.14
    Advanced
    0.14
     Advanced
    0.13
     Ref
    0.13
     patients
    0.12
    apsed
    0.12
     resistant
    0.12
    Activations Density 0.073%

    No Known Activations