© 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. 76301
    Prev
    Next
    INDEX
    Explanations

    ar

    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
     brilliantly
    -0.07
     gov
    -0.06
     Wiring
    -0.06
    陷
    -0.06
    --+
    -0.06
     Guantanamo
    -0.06
    拼
    -0.06
     Wrapped
    -0.06
    sticks
    -0.06
    南省
    -0.06
    POSITIVE LOGITS
    .hw
    0.07
     enumerator
    0.06
     BAR
    0.06
    HG
    0.06
     LAW
    0.06
    Processed
    0.06
     CAST
    0.06
     PE
    0.06
    ["$
    0.06
    _COMPONENT
    0.06
    Activations Density 0.004%

    No Known Activations