© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    entry into force or effectiveness

    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
    iế
    -0.09
    aimassage
    -0.09
     dak
    -0.09
    ILLISE
    -0.08
     Dak
    -0.08
    ãģĶ
    -0.08
    utm
    -0.08
    elopment
    -0.08
    EMP
    -0.08
     Genome
    -0.08
    POSITIVE LOGITS
     effective
    0.32
     effect
    0.29
    effective
    0.26
     Effective
    0.26
     вÑģÑĤÑĥп
    0.25
    Effective
    0.25
     effectiveness
    0.25
     EFFECT
    0.24
     Effect
    0.24
     efect
    0.23
    Activations Density 0.065%

    No Known Activations