© 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. 58098
    Prev
    Next
    INDEX
    Explanations

    Descriptive/telling

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on present‐participle verb forms (words ending in “-ing,” especially multi‐syllable gerunds like “repositioning,” “opening,” “allowing”).

    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
     quizzes
    -0.07
     trag
    -0.06
    eated
    -0.06
    Aw
    -0.06
     Ken
    -0.06
    (dirname
    -0.06
     google
    -0.06
    ">'↵
    -0.06
    .fromRGBO
    -0.06
    .BigDecimal
    -0.06
    POSITIVE LOGITS
    Case
    0.07
     adjusts
    0.06
    isex
    0.06
     좋은
    0.06
     -,
    0.06
     бли
    0.06
    IMP
    0.06
    ,line
    0.06
     reaching
    0.06
     resolving
    0.06
    Activations Density 0.107%

    No Known Activations