© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    content warning, policies, creation, management

    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
    atte
    -0.10
    vara
    -0.10
    obi
    -0.10
     Garr
    -0.10
    GED
    -0.10
    uled
    -0.09
    oly
    -0.09
    AGMA
    -0.09
     hum
    -0.09
     lava
    -0.09
    POSITIVE LOGITS
    ment
    0.24
    ions
    0.20
    editable
    0.18
    iously
    0.18
    ious
    0.18
    .ContextCompat
    0.18
    ful
    0.15
    .ReadAsStringAsync
    0.15
    nea
    0.14
     creation
    0.13
    Activations Density 0.028%

    No Known Activations