© 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. 23-RESID-POST-AA
    11. 104982
    Prev
    Next
    INDEX
    Explanations

    Carl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plan
    -0.06
    lands
    -0.06
     Enrique
    -0.06
     tty
    -0.06
     ride
    -0.06
    theory
    -0.06
     amt
    -0.06
    iris
    -0.06
     Crate
    -0.06
     уб
    -0.06
    POSITIVE LOGITS
    Constants
    0.07
     ola
    0.06
     combust
    0.06
     condensed
    0.06
     algún
    0.06
     lastname
    0.06
    ,$
    0.06
    )<=
    0.06
     何
    0.06
    (ast
    0.06
    Activations Density 0.001%

    No Known Activations