© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35657
    Prev
    Next
    INDEX
    Explanations

    companies that were known for

    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
     become
    -0.10
    Occurred
    -0.09
     works
    -0.09
     be
    -0.08
    525
    -0.08
    _gt
    -0.08
     createState
    -0.08
    atio
    -0.08
     accepted
    -0.08
    ieder
    -0.08
    POSITIVE LOGITS
     exc
    0.17
     score
    0.17
     doing
    0.16
     scores
    0.15
     Doing
    0.15
    doing
    0.14
    åģļ
    0.14
     scored
    0.14
    score
    0.13
     succeed
    0.13
    Activations Density 0.119%

    No Known Activations