© 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. 58862
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    The neuron spotlights numeric measurement phrases—numbers paired with units or quantitative descriptors indicating magnitudes, comparisons, or severity.

    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
    branches
    -0.07
    .Course
    -0.07
     dando
    -0.07
    پ
    -0.07
     nou
    -0.06
     बड़
    -0.06
    (ev
    -0.06
     Professionals
    -0.06
     W
    -0.06
     CLIIIK
    -0.06
    POSITIVE LOGITS
    (rows
    0.07
    -_
    0.06
    estic
    0.06
     Native
    0.06
     GNU
    0.06
    ForKey
    0.06
     вол
    0.06
    題
    0.06
     XCTAssert
    0.06
    τις
    0.06
    Activations Density 0.168%

    No Known Activations