© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57727
    Prev
    Next
    INDEX
    Explanations

    AFP

    np_max-act · gemini-2.0-flash

    The neuron detects the “fp” keyword used in footprint definitions (the “fp_…” lines) in Kicad module code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beri
    -0.07
    thesized
    -0.07
    evaluate
    -0.07
    sequences
    -0.06
    compare
    -0.06
    heads
    -0.06
    Sha
    -0.06
     distinctions
    -0.06
    Из
    -0.06
    oned
    -0.06
    POSITIVE LOGITS
    FP
    0.10
     fp
    0.10
    fp
    0.08
    _fp
    0.08
     inp
    0.08
     bankruptcy
    0.08
     JP
    0.08
    (fp
    0.07
    (#
    0.07
     PSP
    0.07
    Activations Density 0.003%

    No Known Activations