© 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. 24366
    Prev
    Next
    INDEX
    Explanations

    acidic soil and containers

    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
     scrut
    -0.10
     bushes
    -0.09
     creampie
    -0.09
    оÑĢож
    -0.09
    mdl
    -0.09
     sprav
    -0.09
    MethodImpl
    -0.09
    ãģĹãĤĩ
    -0.08
     æ±
    -0.08
     Legislation
    -0.08
    POSITIVE LOGITS
     sph
    0.18
     mul
    0.18
     perl
    0.17
     pe
    0.17
     substrate
    0.17
     Perl
    0.16
     soil
    0.16
     amendments
    0.16
     substr
    0.15
    peat
    0.15
    Activations Density 0.049%

    No Known Activations