© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18453
    Prev
    Next
    INDEX
    Explanations

    explanation of origin and purpose

    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
    pcb
    -0.09
    ivery
    -0.09
    Uvs
    -0.09
    iliz
    -0.09
    ilty
    -0.08
     Proble
    -0.08
    interopRequire
    -0.08
    alled
    -0.08
    _regeneration
    -0.08
    _atts
    -0.08
    POSITIVE LOGITS
     why
    0.25
    why
    0.20
     purpose
    0.20
    为ä»Ģä¹Ī
    0.18
     identity
    0.18
     origin
    0.16
     Why
    0.16
     pourquoi
    0.16
    Why
    0.16
     identities
    0.15
    Activations Density 0.061%

    No Known Activations