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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25409
    Prev
    Next
    INDEX
    Explanations

    Israel, Peres, Sharon

    np_max-act · gemini-2.0-flash

    references to significant political events or figures.

    oai_token-act-pair · gpt-4o-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
    тя
    -0.07
    WOOD
    -0.06
    _dict
    -0.06
     बदल
    -0.06
     shitty
    -0.06
    INVALID
    -0.06
    floor
    -0.06
    (calendar
    -0.06
     wd
    -0.06
     birthday
    -0.06
    POSITIVE LOGITS
     Revised
    0.07
    uated
    0.07
     thông
    0.07
    作用
    0.06
    明
    0.06
     essere
    0.06
    증금
    0.06
     ประ
    0.06
    학기
    0.06
    情况
    0.06
    Activations Density 0.003%

    No Known Activations