© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 111580
    Prev
    Next
    INDEX
    Explanations

    children

    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
     logic
    -0.07
    客
    -0.07
     retarded
    -0.07
    커
    -0.07
     dobře
    -0.07
    -digit
    -0.07
    怖
    -0.07
    ิ่
    -0.06
     Stadt
    -0.06
    lacağı
    -0.06
    POSITIVE LOGITS
     Hole
    0.07
    ี.
    0.06
     installed
    0.06
    PS
    0.06
     Buddy
    0.06
    =wx
    0.06
    -plugins
    0.06
     makeStyles
    0.06
    dG
    0.06
     interviews
    0.06
    Activations Density 0.022%

    No Known Activations