© 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. 35738
    Prev
    Next
    INDEX
    Explanations

    mother and friends

    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
     with
    -0.11
     yerini
    -0.10
    786
    -0.10
     vỼi
    -0.09
     avec
    -0.09
    umbn
    -0.09
    AMPL
    -0.09
     interacting
    -0.09
     aup
    -0.09
     withString
    -0.09
    POSITIVE LOGITS
     whom
    0.19
     who
    0.11
     Wit
    0.10
    who
    0.10
     whose
    0.09
    edi
    0.09
    968
    0.09
     guidance
    0.09
    ipt
    0.09
    æŀ
    0.09
    Activations Density 0.122%

    No Known Activations