© 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. 7-RESID-POST-AA
    11. 61258
    Prev
    Next
    INDEX
    Explanations

    Serbia

    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
     Lynn
    -0.08
    欢
    -0.07
    áme
    -0.06
    Vault
    -0.06
     inadequate
    -0.06
     aktual
    -0.06
     \<^
    -0.06
     быть
    -0.06
    няет
    -0.06
    koliv
    -0.06
    POSITIVE LOGITS
     Serbian
    0.14
     Serbia
    0.13
    enegro
    0.07
     Dublin
    0.07
    gay
    0.07
     Marcos
    0.07
    _UFunction
    0.07
    ć
    0.07
    Cancelar
    0.07
    _az
    0.07
    Activations Density 0.002%

    No Known Activations