© 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. 40195
    Prev
    Next
    INDEX
    Explanations

    avoidance and recent illness

    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
    nip
    -0.10
    AppComponent
    -0.09
    _FS
    -0.09
     controlId
    -0.09
     unspecified
    -0.09
    incip
    -0.08
     colorWith
    -0.08
    rita
    -0.08
    pray
    -0.08
     Cush
    -0.08
    POSITIVE LOGITS
     activities
    0.15
     heavy
    0.12
     Activities
    0.12
     precip
    0.12
     triggers
    0.11
     contact
    0.11
     further
    0.11
     sudden
    0.11
     stren
    0.11
     foods
    0.11
    Activations Density 0.022%

    No Known Activations