© 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. 32406
    Prev
    Next
    INDEX
    Explanations

    distance, far away, apart

    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
     Kraj
    -0.09
    istrovstvÃŃ
    -0.09
     less
    -0.09
     decade
    -0.09
    unce
    -0.08
    hausen
    -0.08
     pushViewController
    -0.08
     Carpenter
    -0.08
    ces
    -0.08
    itore
    -0.08
    POSITIVE LOGITS
     far
    0.44
    è¿ľ
    0.41
    éģł
    0.38
    far
    0.35
     distant
    0.34
     miles
    0.30
     daleko
    0.30
     weit
    0.28
     distance
    0.28
     далеко
    0.28
    Activations Density 0.150%

    No Known Activations