© 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. 7-RESID-POST-AA
    11. 61125
    Prev
    Next
    INDEX
    Explanations

    Cyrillic "А"

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nutzen
    -0.08
    双
    -0.06
    CCA
    -0.06
     Odkazy
    -0.06
     erotik
    -0.06
    _RGB
    -0.06
     })
↵
    -0.06
    wp
    -0.06
     Wie
    -0.06
    _increase
    -0.06
    POSITIVE LOGITS
     Carbon
    0.07
     А
    0.07
    라
    0.07
    /com
    0.06
     Appears
    0.06
    asia
    0.06
    ¬
    0.06
    059
    0.06
     sauces
    0.06
     pellet
    0.06
    Activations Density 0.007%

    No Known Activations