© 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. 121884
    Prev
    Next
    INDEX
    Explanations

    new

    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
     endanger
    -0.07
     kicking
    -0.07
    �
    -0.06
     sweaty
    -0.06
    rooms
    -0.06
    aes
    -0.06
    answers
    -0.06
     exc
    -0.06
    Achie
    -0.06
    ath
    -0.06
    POSITIVE LOGITS
    <char
    0.06
    .Customer
    0.06
    .copyOf
    0.06
    enler
    0.06
    Vien
    0.06
     pirate
    0.06
     자연
    0.06
    imiter
    0.06
     (*(
    0.06
     kappa
    0.06
    Activations Density 0.069%

    No Known Activations