© 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. 50266
    Prev
    Next
    INDEX
    Explanations

    specific needs of

    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
    ager
    -0.11
    iores
    -0.09
     Purpose
    -0.09
    avs
    -0.09
    íĤ¬
    -0.09
    ritt
    -0.08
     Brut
    -0.08
     vyz
    -0.08
     Blast
    -0.08
     Duy
    -0.08
    POSITIVE LOGITS
     situation
    0.21
     project
    0.20
     particular
    0.19
     Situation
    0.16
     projects
    0.16
     individual
    0.16
    é¡¹çĽ®
    0.15
    æĥħåĨµ
    0.14
    project
    0.14
     пÑĢоекÑĤ
    0.14
    Activations Density 0.043%

    No Known Activations