© 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. 35750
    Prev
    Next
    INDEX
    Explanations

    signific related words

    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
    ened
    -0.13
    ted
    -0.10
    iness
    -0.10
    alis
    -0.10
    aub
    -0.10
    avir
    -0.09
    liness
    -0.09
    edl
    -0.09
    ised
    -0.09
    ï¾Ł
    -0.09
    POSITIVE LOGITS
    ificance
    0.14
    ificant
    0.13
    ante
    0.13
    atory
    0.12
    atures
    0.12
    ative
    0.11
    cant
    0.11
    vely
    0.10
    ATURE
    0.10
    æĦıä¹ī
    0.10
    Activations Density 0.016%

    No Known Activations