© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35129
    Prev
    Next
    INDEX
    Explanations

    help/helpful/problematic and its consequence

    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
     underst
    -0.10
    Multiplier
    -0.09
    XA
    -0.09
     Lever
    -0.09
    raq
    -0.09
    :::/
    -0.09
    ingu
    -0.09
    ãĢĢï¾ŀ
    -0.09
     Alexandra
    -0.08
     health
    -0.08
    POSITIVE LOGITS
    ulin
    0.09
     drawn
    0.09
    cept
    0.09
    recover
    0.09
    715
    0.09
     çĻ
    0.09
     comb
    0.09
     overall
    0.09
    _customize
    0.09
     finest
    0.08
    Activations Density 0.046%

    No Known Activations