© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13490
    Prev
    Next
    INDEX
    Explanations

    business again, print out

    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
    contri
    -0.09
     reint
    -0.09
    íħ
    -0.08
     Return
    -0.08
    à¥ĭà¤ķर
    -0.08
    격
    -0.08
    .INSTANCE
    -0.08
    ãĢĢl
    -0.08
     FIN
    -0.08
    (return
    -0.08
    POSITIVE LOGITS
     again
    0.77
    again
    0.59
     Again
    0.56
    Again
    0.53
     novamente
    0.45
     wieder
    0.44
     lại
    0.43
     lagi
    0.43
     igen
    0.42
    åıĪ
    0.41
    Activations Density 0.053%

    No Known Activations