© 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. 51694
    Prev
    Next
    INDEX
    Explanations

    alone in various languages

    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
    538
    -0.09
     Rena
    -0.09
     calloc
    -0.08
    -tm
    -0.08
    anners
    -0.08
     Individual
    -0.08
     Sok
    -0.08
    617
    -0.08
    ìħĢ
    -0.08
     SOUR
    -0.08
    POSITIVE LOGITS
     alone
    1.29
    alone
    1.02
     Alone
    0.94
    -alone
    0.72
     saja
    0.60
     sola
    0.53
     seul
    0.50
     seule
    0.47
     solo
    0.41
     thôi
    0.40
    Activations Density 0.152%

    No Known Activations