© 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. 1424
    Prev
    Next
    INDEX
    Explanations

    list item start indicators

    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
    ÐIJÑĢÑħÑĸв
    -0.10
     activ
    -0.08
    ,
    -0.08
     able
    -0.08
     stalk
    -0.08
     Innovative
    -0.08
    /epl
    -0.08
     could
    -0.08
    stalk
    -0.08
     can
    -0.08
    POSITIVE LOGITS
     embr
    0.10
    embr
    0.09
    acher
    0.09
     stron
    0.09
     sop
    0.08
     lique
    0.08
    ziel
    0.08
    unden
    0.08
     beef
    0.08
     apprec
    0.08
    Activations Density 0.308%

    No Known Activations