© 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. 33251
    Prev
    Next
    INDEX
    Explanations

    as followed by pronoun

    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
     evidenced
    -0.13
     evid
    -0.11
    olin
    -0.09
    mutation
    -0.09
     Recomm
    -0.09
    .ads
    -0.08
    ares
    -0.08
    ÑĤеÑħ
    -0.08
    “;As
    -0.08
    ope
    -0.08
    POSITIVE LOGITS
     they
    0.17
     we
    0.13
     she
    0.12
    ides
    0.12
     medida
    0.11
     you
    0.11
     follows
    0.11
    cert
    0.11
    anse
    0.10
    phy
    0.10
    Activations Density 0.040%

    No Known Activations