© 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. 71228
    Prev
    Next
    INDEX
    Explanations

    up

    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
    (verbose
    -0.07
    цій
    -0.07
    ้าค
    -0.06
    -write
    -0.06
    стин
    -0.06
    城市
    -0.06
    theorem
    -0.06
     púb
    -0.06
    神
    -0.06
     Serialize
    -0.06
    POSITIVE LOGITS
     theft
    0.06
    šit
    0.06
    RowAnimation
    0.06
    SuppressWarnings
    0.06
    StyleSheet
    0.06
     picked
    0.06
     stronger
    0.06
     getMenu
    0.06
    gresql
    0.06
    んな
    0.06
    Activations Density 0.010%

    No Known Activations