© 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. 53748
    Prev
    Next
    INDEX
    Explanations

    fixed, stationary, without relying

    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
     never
    -0.10
    767
    -0.09
     Mine
    -0.09
    odable
    -0.09
    353
    -0.09
     pars
    -0.08
     productivity
    -0.08
     entirely
    -0.08
     underst
    -0.08
     facult
    -0.08
    POSITIVE LOGITS
     fixed
    0.20
    fixed
    0.18
     Fixed
    0.18
     FIXED
    0.17
     rigid
    0.17
    -fixed
    0.16
    åĽºå®ļ
    0.16
    igid
    0.16
    Fixed
    0.16
    .fixed
    0.14
    Activations Density 0.010%

    No Known Activations