© 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. 62631
    Prev
    Next
    INDEX
    Explanations

    landscape and environmental descriptions

    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
    Falsy
    -0.09
     muddy
    -0.09
     streak
    -0.08
    NECTION
    -0.08
    įng
    -0.08
     -*-č\n
    -0.08
    鬼
    -0.08
    echn
    -0.08
    Truthy
    -0.08
     trench
    -0.08
    POSITIVE LOGITS
     landscape
    0.17
     horizon
    0.13
     scene
    0.13
     otherwise
    0.12
     trees
    0.11
    landscape
    0.11
     air
    0.11
     tips
    0.11
     distance
    0.11
     Landscape
    0.10
    Activations Density 0.074%

    No Known Activations