© 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. 24251
    Prev
    Next
    INDEX
    Explanations

    3-chloro- or 3-bromo- prefixes

    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
     glo
    -0.09
     ill
    -0.09
     disproportion
    -0.09
    ging
    -0.09
    stal
    -0.09
     fore
    -0.09
     dur
    -0.09
     fscanf
    -0.09
     breaker
    -0.08
     undermin
    -0.08
    POSITIVE LOGITS
    .xr
    0.10
    cela
    0.09
    prene
    0.09
    owell
    0.09
    زÙĪ
    0.08
    lied
    0.08
    ropol
    0.08
    idders
    0.08
    TRL
    0.08
    arness
    0.08
    Activations Density 0.155%

    No Known Activations