© 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. 29438
    Prev
    Next
    INDEX
    Explanations

    Additions and contrasts

    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
     FOUND
    -0.06
     Lydia
    -0.06
    utations
    -0.06
    /dr
    -0.06
    handlers
    -0.06
     whereby
    -0.06
    许
    -0.06
     RouteServiceProvider
    -0.06
     navCtrl
    -0.06
    _lang
    -0.06
    POSITIVE LOGITS
    ="${
    0.06
    ков
    0.06
    asma
    0.06
    ."<
    0.06
    OVID
    0.06
    short
    0.06
    ---------------
    0.06
     im
    0.06
    RadioButton
    0.06
    MY
    0.06
    Activations Density 0.130%

    No Known Activations