Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94367
    Prev
    Next
    INDEX
    Explanations

    Memberships/subscriptions/dues

    np_max-act · gemini-2.0-flash
    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
    <Member
    -0.06
     committees
    -0.06
     committee
    -0.06
    能力
    -0.06
     NumberOf
    -0.06
    cast
    -0.06
     отк
    -0.06
     <
    -0.06
    .background
    -0.06
    abb
    -0.06
    POSITIVE LOGITS
     télé
    0.07
    くらい
    0.07
    ۲۰۲
    0.07
    REE
    0.06
    mozilla
    0.06
     Oswald
    0.06
    ...",
    0.06
     thuis
    0.06
    toDouble
    0.06
    ้้
    0.06
    Activations Density 0.010%

    No Known Activations