© 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. 58552
    Prev
    Next
    INDEX
    Explanations

    a research organization

    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
    —;
    -0.08
    âĢ¦
    -0.07
     mesel
    -0.07
     multiplic
    -0.07
     recep
    -0.07
    -0.07
     $('#'
    -0.07
    :".$
    -0.06
    ...
    -0.06
     ?
    -0.06
    POSITIVE LOGITS
    ritel
    0.11
    lfw
    0.09
    ÂĢÂĢ
    0.08
    Periph
    0.08
    afx
    0.07
    ******č\n
    0.07
    avatel
    0.07
    οÏģειο
    0.07
     xhttp
    0.07
    EXPR
    0.07
    Activations Density 0.276%

    No Known Activations