© 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. 14362
    Prev
    Next
    INDEX
    Explanations

    to alleviate symptoms

    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
     cured
    -0.11
     addCriterion
    -0.11
    OMP
    -0.09
     تض
    -0.09
     amel
    -0.09
     Nobel
    -0.09
     cris
    -0.09
    ount
    -0.09
     cleans
    -0.09
    ÑĢаÑĩ
    -0.09
    POSITIVE LOGITS
     relief
    0.40
     Relief
    0.34
     relieve
    0.22
     relieved
    0.20
    -rel
    0.19
    rel
    0.18
     symptom
    0.18
     sympt
    0.17
     rele
    0.17
     help
    0.17
    Activations Density 0.093%

    No Known Activations