© 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 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. 11-RESID-POST-AA
    11. 45267
    Prev
    Next
    INDEX
    Explanations

    colorectal cancer screening

    np_max-act · gemini-2.0-flash

    content related to colorectal cancer screening methods and their effectiveness.

    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
     Learning
    -0.06
    <View
    -0.06
     Goal
    -0.06
     MC
    -0.06
    自治
    -0.06
     Mode
    -0.06
    密
    -0.06
     Rick
    -0.06
    縮
    -0.06
     Agility
    -0.06
    POSITIVE LOGITS
    ｛
    0.07
    .pl
    0.07
    	out
    0.06
    회의
    0.06
     która
    0.06
     registros
    0.06
     Firearms
    0.06
     expos
    0.06
    tre
    0.06
    quete
    0.06
    Activations Density 0.009%

    No Known Activations