© 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. 8993
    Prev
    Next
    INDEX
    Explanations

    made a significant impact or contribution

    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
     Chance
    -0.12
    uch
    -0.10
     making
    -0.10
    ä½ľ
    -0.10
     inconvenient
    -0.10
    sec
    -0.10
    Chance
    -0.09
     makeshift
    -0.09
     maken
    -0.09
    andal
    -0.09
    POSITIVE LOGITS
     headlines
    0.23
     waves
    0.21
     enemies
    0.17
    waves
    0.17
     strides
    0.16
     name
    0.15
     Waves
    0.15
    leine
    0.15
     contributions
    0.15
     mark
    0.14
    Activations Density 0.029%

    No Known Activations