© 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. 42540
    Prev
    Next
    INDEX
    Explanations

    contrast and new clauses

    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
     denn
    -0.09
    528
    -0.08
    :\n\n
    -0.08
    uity
    -0.08
    fone
    -0.08
    modifiable
    -0.08
    andel
    -0.08
    lef
    -0.08
    ado
    -0.08
     misc
    -0.08
    POSITIVE LOGITS
    ï¼Įä½Ĩæĺ¯
    0.13
     However
    0.12
     HOWEVER
    0.11
     however
    0.10
     But
    0.10
     BUT
    0.10
    However
    0.10
     etc
    0.09
    огод
    0.09
     UNS
    0.08
    Activations Density 0.068%

    No Known Activations