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. 11-RESID-POST-AA
    6. 35819
    Prev
    Next
    INDEX
    Explanations

    technology

    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_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
     Hernandez
    -0.07
     khẩu
    -0.07
     bild
    -0.06
     Tam
    -0.06
     Yok
    -0.06
     gard
    -0.06
    arg
    -0.06
     Lose
    -0.06
    ucher
    -0.06
     newValue
    -0.06
    POSITIVE LOGITS
     paid
    0.07
     λίγ
    0.06
     soaring
    0.06
    ाफ
    0.06
    ापस
    0.06
    .deleted
    0.06
    gom
    0.06
    Infrastructure
    0.06
     EXISTS
    0.06
     pledges
    0.06
    Activations Density 0.012%

    No Known Activations