© 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. 3607
    Prev
    Next
    INDEX
    Explanations

    such as / example.txt / able to

    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
     ãĥ¼
    -0.10
    ombs
    -0.09
    ICLE
    -0.09
     Barn
    -0.09
     Laden
    -0.09
     pis
    -0.09
    ptron
    -0.09
     Kap
    -0.08
    289
    -0.08
    cca
    -0.08
    POSITIVE LOGITS
    SES
    0.09
     puss
    0.09
     INCIDENT
    0.09
     unc
    0.08
     pneum
    0.08
     Fry
    0.08
    ened
    0.08
     Tul
    0.08
     versa
    0.08
    podob
    0.08
    Activations Density 0.036%

    No Known Activations