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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 94421
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    otyp
    -0.07
    _alias
    -0.07
    (ele
    -0.06
     ç
    -0.06
    .camel
    -0.06
    QualifiedName
    -0.06
    .Month
    -0.06
    (-(
    -0.06
    インタ
    -0.06
    .pt
    -0.06
    POSITIVE LOGITS
     worry
    0.07
     پاسخ
    0.07
    endency
    0.06
     waved
    0.06
    emphasis
    0.06
     مشاركة
    0.06
    gies
    0.06
     hư
    0.06
    جی
    0.06
     Table
    0.06
    Activations Density 0.129%

    No Known Activations