© 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. 61440
    Prev
    Next
    INDEX
    Explanations

    understand or hear

    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
    PU
    -0.09
    iji
    -0.09
    kaç
    -0.09
    TEMPL
    -0.09
    eeper
    -0.08
    utz
    -0.08
    Unnamed
    -0.08
    ijing
    -0.08
     knowing
    -0.08
    /forum
    -0.08
    POSITIVE LOGITS
     understood
    0.22
     intellig
    0.19
     hear
    0.16
     entend
    0.16
     lip
    0.15
     understand
    0.15
     understands
    0.15
     understanding
    0.14
     समà¤Ŀ
    0.14
     heard
    0.14
    Activations Density 0.139%

    No Known Activations