© 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. 76310
    Prev
    Next
    INDEX
    Explanations

    rock/indie music

    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
    Bulletin
    -0.07
    -make
    -0.07
     basement
    -0.07
     convent
    -0.07
     xuất
    -0.07
    uParam
    -0.06
     Communication
    -0.06
    Recording
    -0.06
    ﾆﾆﾆﾆ
    -0.06
    ARRANT
    -0.06
    POSITIVE LOGITS
     Gothic
    0.07
     heute
    0.06
    perfil
    0.06
     Eva
    0.06
    оди
    0.06
     دکتر
    0.06
     Enabled
    0.05
    ificado
    0.05
     Cuando
    0.05
     věd
    0.05
    Activations Density 0.014%

    No Known Activations