© 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. 15-RESID-POST-AA
    11. 57639
    Prev
    Next
    INDEX
    Explanations

    dinner/inner

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ิยม
    -0.07
    forget
    -0.07
     Male
    -0.07
    _pid
    -0.07
    Grow
    -0.06
    pegawai
    -0.06
    Psi
    -0.06
    Tac
    -0.06
     tendency
    -0.06
    arsing
    -0.06
    POSITIVE LOGITS
     dinner
    0.12
     Dinner
    0.11
     dinners
    0.08
     Ens
    0.07
    ερ
    0.07
     سفر
    0.07
     Clover
    0.06
    Equal
    0.06
     supper
    0.06
     �
    0.06
    Activations Density 0.013%

    No Known Activations