© 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. 3-RESID-POST-AA
    11. 95491
    Prev
    Next
    INDEX
    Explanations

    comma

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pixels
    -0.07
    _WIDTH
    -0.06
    .hardware
    -0.06
    /red
    -0.06
    _names
    -0.06
    embedded
    -0.06
    'll
    -0.06
     signalling
    -0.06
     olması
    -0.06
    ependency
    -0.06
    POSITIVE LOGITS
    		
↵
↵
    0.07
    Penn
    0.07
    -elected
    0.07
    ์การ
    0.07
    cly
    0.07
    τες
    0.07
    京
    0.07
    زمان
    0.06
    percentage
    0.06
     Sunder
    0.06
    Activations Density 0.145%

    No Known Activations