© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13646
    Prev
    Next
    INDEX
    Explanations

    is the or is that

    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
     correct
    -0.11
    vre
    -0.09
    vari
    -0.09
     Traits
    -0.09
    åIJĦç§į
    -0.09
    IN
    -0.08
    578
    -0.08
     RED
    -0.08
    ese
    -0.08
     variety
    -0.08
    POSITIVE LOGITS
     respective
    0.25
     respectively
    0.21
     differences
    0.18
     approaches
    0.16
     approach
    0.16
     their
    0.16
    åĪĨåĪ«
    0.16
     difference
    0.15
    difference
    0.14
     Differences
    0.14
    Activations Density 0.112%

    No Known Activations