© 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. 58540
    Prev
    Next
    INDEX
    Explanations

    Histology

    np_max-act · gemini-2.0-flash

    The neuron detects histopathological descriptors—terms relating to tissue classification (e.g. “histologic,” “histological,” “pathological,” “clinicopathological”).

    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
    sap
    -0.07
    (area
    -0.07
     numbering
    -0.07
    _acc
    -0.06
    Thor
    -0.06
     미국
    -0.06
     deg
    -0.06
    amb
    -0.06
    eroon
    -0.06
    Verdana
    -0.06
    POSITIVE LOGITS
    ='".
    0.07
    loe
    0.06
    .operations
    0.06
     tunnel
    0.06
    _putstr
    0.06
    ิ่
    0.06
    ้ท
    0.06
     pH
    0.06
     Tunnel
    0.06
    ۳
    0.06
    Activations Density 0.005%

    No Known Activations