© 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. 571
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    untime
    -0.10
    ENTE
    -0.09
    367
    -0.09
    ucid
    -0.08
    dac
    -0.08
    GINE
    -0.08
     пÑĢиÑĩ
    -0.08
    aklı
    -0.08
     pedestrian
    -0.07
     Bever
    -0.07
    POSITIVE LOGITS
     such
    0.45
    such
    0.38
     like
    0.32
     seperti
    0.28
     zoals
    0.27
     nhÆ°
    0.25
     SUCH
    0.24
    å¦Ĥ
    0.24
     Such
    0.24
     ÑĤакиÑħ
    0.23
    Activations Density 0.069%

    No Known Activations