© 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. 15674
    Prev
    Next
    INDEX
    Explanations

    reaching a point

    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
    eldorf
    -0.09
    .scalablytyped
    -0.09
    åĪº
    -0.09
    ADIUS
    -0.09
    Uvs
    -0.09
     Perspectives
    -0.09
    Endpoints
    -0.09
    740
    -0.09
    utan
    -0.08
    Ùģات
    -0.08
    POSITIVE LOGITS
     point
    0.79
    point
    0.55
     punto
    0.52
    (point
    0.46
    -point
    0.45
     Point
    0.45
    _point
    0.44
    .point
    0.42
    Point
    0.42
    çĤ¹
    0.42
    Activations Density 0.085%

    No Known Activations