© 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. 3-RESID-POST-AA
    11. 95347
    Prev
    Next
    INDEX
    Explanations

    you

    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
     actionPerformed
    -0.07
     blush
    -0.07
    ーニ
    -0.07
     devs
    -0.06
     minib
    -0.06
     Produkte
    -0.06
     Levitra
    -0.06
     functionalities
    -0.06
     vyz
    -0.06
    yaw
    -0.06
    POSITIVE LOGITS
    _memory
    0.07
     діяль
    0.07
     něk
    0.07
     DataType
    0.06
    gregar
    0.06
     eğit
    0.06
    若
    0.06
     söyl
    0.06
     mỹ
    0.06
    _SELECTION
    0.06
    Activations Density 0.028%

    No Known Activations