Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95190
    Prev
    Next
    INDEX
    Explanations

    otion

    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
     warehouse
    -0.07
     ksi
    -0.07
     vigilant
    -0.07
     handy
    -0.07
     муз
    -0.07
    (Constant
    -0.06
     Maven
    -0.06
     استر
    -0.06
     vegan
    -0.06
     seeds
    -0.06
    POSITIVE LOGITS
     emotionally
    0.14
     emoc
    0.07
     sentiment
    0.07
     Emerging
    0.07
     emotions
    0.07
    /em
    0.06
     emot
    0.06
     sentient
    0.06
    ancer
    0.06
     storyboard
    0.06
    Activations Density 0.031%

    No Known Activations