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. 27-RESID-POST-AA
    6. 108989
    Prev
    Next
    INDEX
    Explanations

    mixed data and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atum
    -0.07
    'http
    -0.07
    TextInput
    -0.07
    iento
    -0.07
     更
    -0.07
     premi
    -0.07
     clas
    -0.07
     واحدة
    -0.07
     여자
    -0.06
     ciphertext
    -0.06
    POSITIVE LOGITS
    _Product
    0.06
     PdfPCell
    0.06
    (Is
    0.06
    닉
    0.06
     savory
    0.06
    .labelControl
    0.06
     erfahren
    0.06
    Kyle
    0.06
    .Description
    0.06
    layouts
    0.05
    Activations Density 0.348%

    No Known Activations