© 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. 123919
    Prev
    Next
    INDEX
    Explanations

    are is

    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
    inning
    -0.07
     Nor
    -0.07
     Angebot
    -0.07
     permite
    -0.06
     Kod
    -0.06
    .mar
    -0.06
     WH
    -0.06
    าว
    -0.06
     баз
    -0.06
     Theft
    -0.06
    POSITIVE LOGITS
    olygon
    0.08
    <>↵
    0.07
     dilation
    0.07
    ۳۶
    0.06
     CGPoint
    0.06
    香港
    0.06
    ไทย
    0.06
     morphology
    0.06
     zp
    0.06
     definitive
    0.06
    Activations Density 0.008%

    No Known Activations