© 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. 15-RESID-POST-AA
    11. 14330
    Prev
    Next
    INDEX
    Explanations

    neighbor

    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
     сто
    -0.07
    だよ
    -0.06
    ellipsis
    -0.06
    "]');↵
    -0.06
    ीम
    -0.06
    UG
    -0.06
    เหล
    -0.06
    .AUTO
    -0.06
     بين
    -0.06
     boş
    -0.06
    POSITIVE LOGITS
     pretend
    0.07
     getObject
    0.07
     immobil
    0.06
     tomb
    0.06
     victory
    0.06
    .onreadystatechange
    0.06
     représent
    0.06
     стад
    0.06
     Міністер
    0.06
     gözlem
    0.06
    Activations Density 0.004%

    No Known Activations