© 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. 36926
    Prev
    Next
    INDEX
    Explanations

    along with statements

    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
     Combined
    -0.11
    741
    -0.09
    addTo
    -0.09
    erged
    -0.09
    Combined
    -0.08
    uras
    -0.08
     Juliet
    -0.08
    illard
    -0.08
    712
    -0.08
    aco
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.33
     along
    0.31
     kèm
    0.30
     ÙĩÙħراÙĩ
    0.28
     together
    0.27
     à¸ŀร
    0.27
     plus
    0.26
     вмеÑģÑĤе
    0.25
     accompanied
    0.25
    along
    0.24
    Activations Density 0.378%

    No Known Activations