© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    after

    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
     afternoon
    -0.09
    spam
    -0.09
    asta
    -0.09
     Scal
    -0.09
    ĤŃ
    -0.08
     inaug
    -0.08
    bastian
    -0.08
    obre
    -0.08
    atu
    -0.08
    ÑģÑĤÑĥп
    -0.08
    POSITIVE LOGITS
    words
    0.25
    word
    0.21
    WARDS
    0.21
    effects
    0.20
    thought
    0.20
    ward
    0.20
    wards
    0.18
    gl
    0.16
    care
    0.16
    ViewInit
    0.16
    Activations Density 0.039%

    No Known Activations