© 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. 55713
    Prev
    Next
    INDEX
    Explanations

    starting new sentences

    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
     actually
    -0.10
     Hend
    -0.08
    aska
    -0.08
    ipeg
    -0.08
    agas
    -0.08
     nearly
    -0.08
    etch
    -0.08
    edback
    -0.08
     brom
    -0.08
    604
    -0.08
    POSITIVE LOGITS
    ¶Į
    0.13
     consent
    0.11
     Consent
    0.10
     she
    0.09
     consenting
    0.09
    ewan
    0.09
     она
    0.09
    ãģ¾ãģļ
    0.08
    aln
    0.08
    à¹Ģà¸ĺà¸Ń
    0.08
    Activations Density 0.575%

    No Known Activations