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. 11-RESID-POST-AA
    6. 123212
    Prev
    Next
    INDEX
    Explanations

    know

    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
    amba
    -0.08
    V
    -0.07
    وير
    -0.07
     merch
    -0.07
    usr
    -0.07
     guitar
    -0.06
    EFI
    -0.06
     save
    -0.06
    jh
    -0.06
    렬
    -0.06
    POSITIVE LOGITS
     thanked
    0.07
     csrf
    0.06
     Assume
    0.06
     yararlan
    0.06
     tehdy
    0.06
    dsa
    0.06
    .Utility
    0.06
    .report
    0.06
     Germany
    0.06
     bloginfo
    0.06
    Activations Density 0.048%

    No Known Activations