© 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. 19-RESID-POST-AA
    11. 91863
    Prev
    Next
    INDEX
    Explanations

    guidance and support

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    】↵
    -0.07
     achievable
    -0.07
     استاندارد
    -0.06
     Cabin
    -0.06
    -з
    -0.06
    )#
    -0.06
    掉
    -0.06
    ("|
    -0.06
    crew
    -0.06
    armed
    -0.06
    POSITIVE LOGITS
    hood
    0.06
     yeniden
    0.06
     öğretmen
    0.06
     Spaces
    0.06
     Frag
    0.06
     crippling
    0.06
     percussion
    0.06
    仕
    0.06
     conseils
    0.06
     livestock
    0.06
    Activations Density 0.180%

    No Known Activations