© 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. 56794
    Prev
    Next
    INDEX
    Explanations

    organizations and companies

    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
     whom
    -0.10
    aze
    -0.09
    DEX
    -0.09
     ÑıкÑĥ
    -0.09
     gpointer
    -0.09
    iner
    -0.09
     memor
    -0.09
     коÑĤоÑĢого
    -0.09
    िड
    -0.09
    oret
    -0.08
    POSITIVE LOGITS
     dedicated
    0.21
     devoted
    0.18
    çĶ¨äºİ
    0.17
     responsible
    0.17
     designed
    0.16
     used
    0.14
     meant
    0.14
     intended
    0.14
     dealing
    0.14
    è´Łè´£
    0.14
    Activations Density 0.308%

    No Known Activations