© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    conditional language

    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
    尽管
    -0.09
    ENDIF
    -0.09
     zwar
    -0.09
    olon
    -0.08
    idd
    -0.08
    ormsg
    -0.08
    è®
    -0.08
     Schn
    -0.08
    ston
    -0.08
    èĻ½
    -0.08
    POSITIVE LOGITS
     if
    0.24
     If
    0.19
     nếu
    0.19
    ï¼Įå¦Ĥæŀľ
    0.17
     jika
    0.17
     еÑģли
    0.17
    If
    0.16
    å¦Ĥæŀľ
    0.16
     यद
    0.16
     à¤ħà¤Ĺर
    0.16
    Activations Density 0.214%

    No Known Activations