© 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. 40376
    Prev
    Next
    INDEX
    Explanations

    impact and effects

    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
    .createFrom
    -0.10
    awan
    -0.09
    ILON
    -0.09
    Unsafe
    -0.08
    unsafe
    -0.08
     reap
    -0.08
    osg
    -0.08
     åĮ
    -0.08
    678
    -0.08
    elli
    -0.08
    POSITIVE LOGITS
     impact
    0.56
     effects
    0.49
     effect
    0.46
     Impact
    0.44
    impact
    0.44
     impacts
    0.41
    Impact
    0.40
     Effects
    0.38
    Effects
    0.35
    å½±åĵį
    0.33
    Activations Density 0.141%

    No Known Activations