© 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. 51239
    Prev
    Next
    INDEX
    Explanations

    project planning and specifications

    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
    exter
    -0.09
    appa
    -0.09
    láda
    -0.08
    elic
    -0.08
    ТÐŀ
    -0.08
    elden
    -0.08
    osg
    -0.08
    Å¡ov
    -0.08
    rescia
    -0.08
    resse
    -0.08
    POSITIVE LOGITS
     ag
    0.10
     Pear
    0.09
    orge
    0.09
    ique
    0.08
    iph
    0.08
    /-
    0.08
     needle
    0.08
    íģ¼
    0.08
     kot
    0.08
     sab
    0.08
    Activations Density 0.387%

    No Known Activations