© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    thoughts

    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
     desarroll
    -0.07
     likewise
    -0.06
     Sous
    -0.06
    xn
    -0.06
     Fn
    -0.06
     Quality
    -0.06
     système
    -0.06
    403
    -0.06
    Suddenly
    -0.06
     улучш
    -0.06
    POSITIVE LOGITS
    destruct
    0.07
    穿
    0.07
    ucing
    0.07
     scrut
    0.07
     kino
    0.06
     ری
    0.06
     Coordinator
    0.06
    erv
    0.06
    ван
    0.06
    ayi
    0.06
    Activations Density 0.035%

    No Known Activations