© 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. 11-RESID-POST-AA
    11. 53859
    Prev
    Next
    INDEX
    Explanations

    directions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Robots
    -0.07
     λα
    -0.07
     Με
    -0.07
    错
    -0.06
    คอม
    -0.06
    Ec
    -0.06
     пр
    -0.06
    еко
    -0.06
     për
    -0.06
     بسیار
    -0.06
    POSITIVE LOGITS
     grö
    0.08
     nerv
    0.07
    stre
    0.06
    manage
    0.06
     gamb
    0.06
    _pack
    0.06
     روست
    0.06
     Cristina
    0.06
    459
    0.06
     yeri
    0.06
    Activations Density 0.023%

    No Known Activations