© 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
    5. 50-RESID-POST-GF
    7. 37888
    Prev
    Next
    INDEX
    Explanations

    helping professionals treat

    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
     nurt
    -0.11
    adh
    -0.10
     geg
    -0.09
    ::::::::::::
    -0.08
    μη
    -0.08
     nurturing
    -0.08
     æ¢
    -0.08
    /use
    -0.08
    criptor
    -0.08
    aced
    -0.08
    POSITIVE LOGITS
     helping
    0.18
    帮åĬ©
    0.17
     minister
    0.16
     treating
    0.15
     giúp
    0.15
    çħ§
    0.14
     interactions
    0.14
     supporting
    0.13
     helps
    0.13
    help
    0.13
    Activations Density 0.217%

    No Known Activations