© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41862
    Prev
    Next
    INDEX
    Explanations

    electrical intensity and duration

    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
     McCabe
    -0.10
     pand
    -0.09
    coe
    -0.09
    wind
    -0.09
     Mayer
    -0.09
     infected
    -0.09
    ez
    -0.09
     ragaz
    -0.08
    hawks
    -0.08
    reopen
    -0.08
    POSITIVE LOGITS
     electric
    0.25
     Electric
    0.21
     shocks
    0.19
    çĶµ
    0.19
     shocking
    0.19
     electrical
    0.19
     electricity
    0.19
     shock
    0.19
     Shock
    0.18
    Electric
    0.17
    Activations Density 0.064%

    No Known Activations