Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 83706
    Prev
    Next
    INDEX
    Explanations

    AB

    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
     Pavilion
    -0.07
     Southwest
    -0.07
     Daddy
    -0.06
     Goldberg
    -0.06
     obsolete
    -0.06
    بود
    -0.06
    pq
    -0.06
     paternal
    -0.06
     '-')
    -0.06
    ğiz
    -0.06
    POSITIVE LOGITS
     evolving
    0.07
     nachází
    0.07
    εν
    0.06
    为
    0.06
     رمز
    0.06
     gioc
    0.06
     {(
    0.06
    及
    0.06
     PROT
    0.06
     �
    0.06
    Activations Density 0.121%

    No Known Activations