© 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. 61726
    Prev
    Next
    INDEX
    Explanations

    submit paperwork

    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
    ington
    -0.11
    hte
    -0.11
    ãģĬãĤĬ
    -0.10
    LIK
    -0.10
    ermen
    -0.10
    angelo
    -0.09
    ãģªãģĮãĤī
    -0.09
    agos
    -0.09
    ISTIC
    -0.09
    oft
    -0.09
    POSITIVE LOGITS
    ter
    0.28
    ting
    0.25
    ochond
    0.17
    tee
    0.15
    TING
    0.15
    tees
    0.14
    te
    0.11
    ively
    0.11
    .prevent
    0.11
    ilda
    0.11
    Activations Density 0.020%

    No Known Activations