© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29592
    Prev
    Next
    INDEX
    Explanations

    Reviews and commentaries

    np_max-act · gemini-2.0-flash

    The neuron responds to terms used for criticism or evaluative commentary (e.g. crítica, superficialidad, falta de pensamiento crítico).

    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
    Tube
    -0.06
    Rock
    -0.06
     Rick
    -0.06
    ��
    -0.06
    영상
    -0.06
     callable
    -0.06
     Lantern
    -0.06
    -board
    -0.06
    ?>
    ↵
    ↵
    -0.06
    brown
    -0.06
    POSITIVE LOGITS
    lazy
    0.07
     سک
    0.06
    createView
    0.06
    `↵
    0.06
    ;"><
    0.06
    declare
    0.06
    ạy
    0.06
    nl
    0.06
     اک
    0.06
     deben
    0.06
    Activations Density 0.085%

    No Known Activations