© 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. 59168
    Prev
    Next
    INDEX
    Explanations

    increased or higher average

    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
     excess
    -0.12
    urai
    -0.10
    afone
    -0.09
     balance
    -0.09
    Äĥng
    -0.09
    ause
    -0.09
     Kre
    -0.09
    addir
    -0.09
    awi
    -0.09
     Dense
    -0.09
    POSITIVE LOGITS
     levels
    0.14
     risk
    0.13
     stress
    0.13
     frag
    0.13
    stress
    0.13
     vulnerability
    0.12
     likelihood
    0.12
    é£İéĻ©
    0.11
     Risk
    0.11
     complexity
    0.11
    Activations Density 0.051%

    No Known Activations