© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 79630
    Prev
    Next
    INDEX
    Explanations

    fatty acids

    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
     double
    -0.07
    .Register
    -0.07
    -type
    -0.06
     Begin
    -0.06
     incoming
    -0.06
    Empty
    -0.06
     kara
    -0.06
    combination
    -0.06
     canada
    -0.06
     CSV
    -0.06
    POSITIVE LOGITS
     anv
    0.07
    installer
    0.07
    .bpm
    0.07
    HQ
    0.07
    .ast
    0.06
    BootTest
    0.06
    ิตร
    0.06
     Jana
    0.06
    .getResources
    0.06
    ори
    0.06
    Activations Density 0.001%

    No Known Activations