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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 54729
    Prev
    Next
    INDEX
    Explanations

    and impact

    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
    ï½Ŀ
    -0.10
     billig
    -0.09
    _INLINE
    -0.09
    expo
    -0.09
     infix
    -0.09
     Salisbury
    -0.08
     hourly
    -0.08
    .innerHeight
    -0.08
    غر
    -0.08
    icari
    -0.08
    POSITIVE LOGITS
     persistence
    0.17
    Persistence
    0.17
     breakdown
    0.16
     partition
    0.16
     Persistence
    0.15
     Persistent
    0.13
     Partition
    0.13
     fate
    0.13
     Fate
    0.12
     half
    0.12
    Activations Density 0.013%

    No Known Activations