© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    isolated from each other

    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
     Deferred
    -0.10
    quiet
    -0.09
    Deferred
    -0.09
     ìĪĻ
    -0.09
    andest
    -0.08
    _backup
    -0.08
     Boss
    -0.08
    yne
    -0.08
     Glo
    -0.08
     dere
    -0.08
    POSITIVE LOGITS
     isolation
    0.30
     isolated
    0.29
     isol
    0.25
     isolate
    0.24
    isol
    0.22
    éļĶ
    0.21
    æ²Ļ
    0.20
     sand
    0.19
     sandbox
    0.17
     Sand
    0.16
    Activations Density 0.100%

    No Known Activations