© 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. 53681
    Prev
    Next
    INDEX
    Explanations

    business specific terms

    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
    ctors
    -0.10
    ctor
    -0.09
    undi
    -0.09
     olmasına
    -0.08
    lez
    -0.08
    bsd
    -0.08
    _requested
    -0.08
    ceptor
    -0.08
    953
    -0.08
    ULA
    -0.08
    POSITIVE LOGITS
    为äºĨ
    0.45
     inorder
    0.40
     afin
    0.36
     ÑĩÑĤобÑĭ
    0.36
     nhằm
    0.35
     Äijá»ĥ
    0.32
     Ñīоб
    0.28
     aby
    0.27
    à¹Ģà¸ŀ
    0.24
    à¹Įà¹Ģà¸ŀ
    0.24
    Activations Density 0.309%

    No Known Activations