© 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. 134
    Prev
    Next
    INDEX
    Explanations

    Congress represented, this problem, detection using

    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
    oli
    -0.10
    åĪ°äºĨ
    -0.10
    ic
    -0.10
    -to
    -0.10
     Hat
    -0.10
    essel
    -0.09
    dit
    -0.09
    ella
    -0.09
    otes
    -0.09
    è¾¾åĪ°
    -0.09
    POSITIVE LOGITS
     extent
    0.23
     detriment
    0.18
     tune
    0.15
     extents
    0.15
    extent
    0.14
    venge
    0.13
    vert
    0.13
    ç¨ĭ度
    0.12
     ratio
    0.12
    _extent
    0.11
    Activations Density 0.341%

    No Known Activations