© 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. 34093
    Prev
    Next
    INDEX
    Explanations

    iodine compounds

    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
     CO
    -0.09
    éħ¸
    -0.09
     Babe
    -0.09
    OSP
    -0.09
    ickers
    -0.09
    ¦
    -0.09
    æķ¦
    -0.09
    eria
    -0.08
     blended
    -0.08
    heat
    -0.08
    POSITIVE LOGITS
     iod
    0.32
    iod
    0.24
     thyroid
    0.19
    IOD
    0.18
     hal
    0.18
     Hal
    0.17
    hal
    0.16
    $I
    0.15
     halo
    0.13
    iode
    0.13
    Activations Density 0.047%

    No Known Activations