© 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. 22710
    Prev
    Next
    INDEX
    Explanations

    "once upon a time"

    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
     persona
    -0.07
    chalk
    -0.07
    gatsby
    -0.06
     {...
    -0.06
     segmentation
    -0.06
     مثلا
    -0.06
    σιμο
    -0.06
     repreh
    -0.06
    含
    -0.06
     darling
    -0.06
    POSITIVE LOGITS
    Of
    0.07
    .active
    0.06
     bitk
    0.06
    lamak
    0.06
    _Of
    0.06
    (bg
    0.06
    ="#"><
    0.06
     Nor
    0.06
    ifie
    0.06
    <class
    0.06
    Activations Density 0.008%

    No Known Activations