© 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. 69227
    Prev
    Next
    INDEX
    Explanations

    webpage layout code

    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
    .mon
    -0.06
    .ls
    -0.06
    `
↵
    -0.06
    -this
    -0.06
     dors
    -0.06
    getStatus
    -0.06
    other
    -0.06
     otros
    -0.06
     Ka
    -0.06
    pecies
    -0.06
    POSITIVE LOGITS
    빈
    0.06
     зал
    0.06
    �
    0.06
    から
    0.06
     Rover
    0.06
     گزارش
    0.06
    ?
    0.06
     gr
    0.06
    ()+"
    0.06
    異
    0.06
    Activations Density 0.011%

    No Known Activations