© 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. 25131
    Prev
    Next
    INDEX
    Explanations

    validates compliance

    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
    <|begin_of_text|>
    -0.09
    *=*=
    -0.08
    ******č\n
    -0.08
    iê
    -0.08
    .Formatter
    -0.08
    ÌĨ
    -0.08
    .Messaging
    -0.08
    łéĻ¤
    -0.08
    ÑĴ
    -0.08
     UIStoryboard
    -0.08
    POSITIVE LOGITS
    SystemService
    0.08
    .scalablytyped
    0.08
    .MixedReality
    0.07
     practition
    0.07
    tin
    0.07
     unmist
    0.07
    COPE
    0.07
    ese
    0.07
    _lineno
    0.07
    \(
    0.07
    Activations Density 0.023%

    No Known Activations