© 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. 43547
    Prev
    Next
    INDEX
    Explanations

    is/was/are + state or action

    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
     unaffected
    -0.11
     Vie
    -0.10
     traumat
    -0.10
    halt
    -0.09
     Hunger
    -0.09
     eyel
    -0.09
     hurting
    -0.09
    åĨ
    -0.09
     disin
    -0.08
    amaged
    -0.08
    POSITIVE LOGITS
     prescribed
    0.13
    emic
    0.13
     referred
    0.12
     stable
    0.11
     admitted
    0.10
     carriers
    0.10
    arth
    0.10
     Stable
    0.10
    cla
    0.10
     diagnosed
    0.10
    Activations Density 0.080%

    No Known Activations