Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 91682
    Prev
    Next
    INDEX
    Explanations

    UI activities

    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
    ết
    -0.08
    .dsl
    -0.07
     promotions
    -0.07
     succesfully
    -0.07
     copp
    -0.06
     ケ
    -0.06
    cac
    -0.06
     Teddy
    -0.06
     Confirm
    -0.06
    defgroup
    -0.06
    POSITIVE LOGITS
    σταση
    0.06
    =UTF
    0.06
    emer
    0.06
    Poster
    0.06
     discount
    0.06
    -text
    0.06
    _optional
    0.06
    uição
    0.06
     Log
    0.05
     giving
    0.05
    Activations Density 0.079%

    No Known Activations