© 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. 19-RESID-POST-AA
    11. 58990
    Prev
    Next
    INDEX
    Explanations

    According

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    徽
    -0.07
     ATTRIBUTE
    -0.06
    ách
    -0.06
     lParam
    -0.06
    ifr
    -0.06
    فل
    -0.06
    washer
    -0.06
     utility
    -0.06
    criptions
    -0.06
     Cottage
    -0.06
    POSITIVE LOGITS
    Environmental
    0.07
     найкра
    0.06
     india
    0.06
    „ط
    0.06
    　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　
    0.06
     ric
    0.06
     CCT
    0.06
    (ok
    0.06
    Ho
    0.06
    ===========
    0.06
    Activations Density 0.325%

    No Known Activations