© 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. 27688
    Prev
    Next
    INDEX
    Explanations

    has followed by common words/phrases, hashtags, proper nouns

    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
    ÅĽmy
    -0.12
    ÅĽcie
    -0.11
    zza
    -0.10
     Ñģами
    -0.10
    ees
    -0.10
    hardt
    -0.10
     Blanch
    -0.09
    tos
    -0.09
    537
    -0.09
     themselves
    -0.09
    POSITIVE LOGITS
    nt
    0.18
    OwnProperty
    0.17
    htag
    0.16
    htags
    0.14
     been
    0.14
    /is
    0.13
    bro
    0.13
     sido
    0.13
    BeenCalled
    0.12
    htable
    0.12
    Activations Density 0.102%

    No Known Activations