© 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. 12914
    Prev
    Next
    INDEX
    Explanations

    column names or indices

    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
     Cummings
    -0.09
    actionDate
    -0.09
    oldemort
    -0.09
    rouch
    -0.09
    117
    -0.09
    GuidId
    -0.09
    ENDOR
    -0.08
    EdgeInsets
    -0.08
     apprec
    -0.08
    imon
    -0.08
    POSITIVE LOGITS
    31
    0.20
    35
    0.18
    32
    0.17
    30
    0.17
    33
    0.16
    34
    0.15
    36
    0.14
    40
    0.14
    37
    0.14
    39
    0.12
    Activations Density 0.057%

    No Known Activations