© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 36425
    Prev
    Next
    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash

    programming-style identifiers and schema tokens—especially snake_case field names, “id”/“_id” references, and numeric-laden tokens.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ImageField
    -0.06
    妃
    -0.06
     Yıl
    -0.06
     receptor
    -0.06
    inent
    -0.06
    valor
    -0.06
     Mädchen
    -0.06
    �
    -0.06
    股份有限公司
    -0.06
    Clazz
    -0.06
    POSITIVE LOGITS
     helf
    0.08
    IGHT
    0.07
    >alert
    0.07
    DATABASE
    0.07
    áz
    0.07
     futures
    0.07
    lah
    0.06
     zich
    0.06
     awake
    0.06
     негатив
    0.06
    Activations Density 1.308%

    No Known Activations