© 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. 41241
    Prev
    Next
    INDEX
    Explanations

    zero-sum, zero-shot, zero padded

    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
    rial
    -0.09
    ince
    -0.08
     Devil
    -0.08
    ottom
    -0.08
    LEM
    -0.08
    resi
    -0.08
    ris
    -0.08
    phil
    -0.08
     advantageous
    -0.08
    ños
    -0.08
    POSITIVE LOGITS
    ed
    0.17
    ing
    0.16
     tolerance
    0.15
    es
    0.15
    th
    0.15
    zero
    0.14
    -sum
    0.14
    ToOne
    0.14
    WidthSpace
    0.13
    conf
    0.13
    Activations Density 0.031%

    No Known Activations