© 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. 44526
    Prev
    Next
    INDEX
    Explanations

    electrical impulses

    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
     Ellison
    -0.09
     Radiation
    -0.09
    _IW
    -0.08
     Frederick
    -0.08
     Synopsis
    -0.08
     Pist
    -0.08
    é¨
    -0.08
    antan
    -0.08
    gow
    -0.08
    EMA
    -0.08
    POSITIVE LOGITS
     dep
    0.33
     firing
    0.20
    dep
    0.18
     Hodg
    0.18
     electrical
    0.18
     Dep
    0.17
     dép
    0.17
     electric
    0.16
     voltage
    0.16
     exc
    0.16
    Activations Density 0.034%

    No Known Activations