© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25196
    Prev
    Next
    INDEX
    Explanations

    non-English languages

    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
     dum
    -0.06
    珍
    -0.06
     CHR
    -0.06
    —
    -0.06
    sheet
    -0.06
     dn
    -0.05
     predicting
    -0.05
     Cra
    -0.05
     notre
    -0.05
     de
    -0.05
    POSITIVE LOGITS
     secara
    0.07
    ιο
    0.07
    امت
    0.07
     Пос
    0.07
     zbyt
    0.07
     метод
    0.07
    ètre
    0.06
     záznam
    0.06
    ertype
    0.06
    ulação
    0.06
    Activations Density 0.890%

    No Known Activations