© 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. 19456
    Prev
    Next
    INDEX
    Explanations

    Temperature, templete, temerity

    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
    anela
    -0.09
    agonal
    -0.09
    Mob
    -0.09
    çŃij
    -0.09
     penetr
    -0.09
    rophic
    -0.09
    imity
    -0.09
     barn
    -0.09
    rient
    -0.08
     zar
    -0.08
    POSITIVE LOGITS
    pest
    0.17
    pliers
    0.15
    plete
    0.13
    PERATURE
    0.13
    ps
    0.13
    escal
    0.13
    orarily
    0.12
     ÑģамÑĭм
    0.12
    eltas
    0.12
    perature
    0.12
    Activations Density 0.030%

    No Known Activations