© 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. 49930
    Prev
    Next
    INDEX
    Explanations

    controlar, control, controlador

    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
    ials
    -0.10
     Schwe
    -0.10
    elsen
    -0.09
    dac
    -0.09
    aways
    -0.09
     hous
    -0.08
    yb
    -0.08
    y
    -0.08
    nova
    -0.08
    ÑıÑĩ
    -0.08
    POSITIVE LOGITS
    .Monad
    0.20
     freak
    0.19
    ateral
    0.17
     Freak
    0.16
    leur
    0.16
    led
    0.16
    -Allow
    0.15
    (control
    0.13
    uce
    0.13
    adores
    0.13
    Activations Density 0.022%

    No Known Activations