© 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. 58327
    Prev
    Next
    INDEX
    Explanations

    of/for

    np_max-act · gemini-2.0-flash

    pharmaceutical terms related to medical procedures and outcomes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to floating-point decimal numbers (i.e. fractional values with several digits after a decimal point).

    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
    ��
    -0.06
    (Py
    -0.06
    _skip
    -0.06
     Sud
    -0.06
    urface
    -0.06
    (patient
    -0.06
     Builders
    -0.06
     Nil
    -0.06
    .MSG
    -0.06
     ordin
    -0.06
    POSITIVE LOGITS
    ハ
    0.06
    keley
    0.06
    ัพย
    0.06
     excer
    0.06
    points
    0.06
    Context
    0.06
    sf
    0.06
    ()-
    0.06
    -bre
    0.06
    brate
    0.06
    Activations Density 0.160%

    No Known Activations