© 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. 53817
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
     Hartford
    -0.08
     Shapiro
    -0.06
     Elections
    -0.06
    一个人
    -0.06
    قم
    -0.06
     Mn
    -0.06
     Boone
    -0.06
    سوب
    -0.06
     編
    -0.06
     Thompson
    -0.06
    POSITIVE LOGITS
    equ
    0.07
     hö
    0.07
    。',↵
    0.06
    .semantic
    0.06
    /unit
    0.06
    स
    0.06
    eci
    0.06
    nout
    0.06
    ?",↵
    0.06
    ultiply
    0.06
    Activations Density 0.008%

    No Known Activations