© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 13948
    Prev
    Next
    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash

    list structure markers and section headings (enumerated items and outline headings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mortality
    -0.06
     advantages
    -0.06
     conservation
    -0.06
    imps
    -0.06
    鲜
    -0.06
     Oz
    -0.06
     مباش
    -0.06
     خودرو
    -0.06
    oj
    -0.06
    死
    -0.06
    POSITIVE LOGITS
     nút
    0.07
    =url
    0.07
     XBOOLE
    0.07
    (rep
    0.06
    -Core
    0.06
    [js
    0.06
    .managed
    0.06
    (users
    0.06
    oplevel
    0.06
     attr
    0.06
    Activations Density 0.089%

    No Known Activations