© 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. 60162
    Prev
    Next
    INDEX
    Explanations

    harshness, difficulty, severity

    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
     forcibly
    -0.10
     forcefully
    -0.09
    ë²Ķ
    -0.09
    /loose
    -0.09
     Deep
    -0.09
     attent
    -0.08
    .:.:
    -0.08
    DIRECTORY
    -0.08
     sond
    -0.08
     gum
    -0.08
    POSITIVE LOGITS
     harsh
    0.50
     hard
    0.37
     tough
    0.37
     жеÑģÑĤ
    0.33
     severe
    0.31
     rough
    0.30
     Cru
    0.29
     hardness
    0.29
     severity
    0.28
    hard
    0.28
    Activations Density 0.126%

    No Known Activations