© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61333
    Prev
    Next
    INDEX
    Explanations

    "or" variations and alternatives

    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
    802
    -0.09
     ÙĪص
    -0.09
     Khal
    -0.09
     forg
    -0.08
    ingo
    -0.08
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
     McGr
    -0.08
    iras
    -0.08
    hta
    -0.08
    atra
    -0.08
    POSITIVE LOGITS
     nor
    0.17
     variations
    0.12
     any
    0.11
     variants
    0.11
     variant
    0.10
    ä»»ä½ķ
    0.10
    nor
    0.10
     variation
    0.10
     simil
    0.10
     etc
    0.10
    Activations Density 0.051%

    No Known Activations