© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 36739
    Prev
    Next
    INDEX
    Explanations

    unethical

    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
     آموز
    -0.06
     Question
    -0.06
     keyboards
    -0.06
     anticip
    -0.06
     sacrific
    -0.06
     fian
    -0.05
    建
    -0.05
     نگ
    -0.05
    leaning
    -0.05
     dá
    -0.05
    POSITIVE LOGITS
    syntax
    0.08
    737
    0.08
     unethical
    0.08
     setTime
    0.07
    ethical
    0.07
    (Runtime
    0.07
     навк
    0.06
     натураль
    0.06
     arttır
    0.06
    ocom
    0.06
    Activations Density 0.003%

    No Known Activations