© 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. 11-RESID-POST-AA
    11. 47717
    Prev
    Next
    INDEX
    Explanations

    Magazines

    np_max-act · gemini-2.0-flash

    content that discusses explicit sexual scenarios, particularly involving cultural and racial themes.

    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
    Odd
    -0.07
    ritz
    -0.06
     camp
    -0.06
     Ari
    -0.06
     Bronze
    -0.06
     indis
    -0.06
    >({↵
    -0.06
    ारक
    -0.06
    Memory
    -0.06
    letion
    -0.06
    POSITIVE LOGITS
    各种
    0.07
     numerous
    0.07
     nakonec
    0.07
    (Error
    0.06
    .setUp
    0.06
    InnerHTML
    0.06
    osos
    0.06
     SATA
    0.06
    .BigDecimal
    0.06
    _VALID
    0.06
    Activations Density 0.005%

    No Known Activations