© 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. 20740
    Prev
    Next
    INDEX
    Explanations

    lead

    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
    čast
    -0.07
    脱
    -0.07
    .pickle
    -0.06
    _EQUAL
    -0.06
    煙
    -0.06
    นม
    -0.06
    Century
    -0.06
    Universal
    -0.06
    inery
    -0.06
    xdd
    -0.06
    POSITIVE LOGITS
     अग
    0.07
    ihan
    0.07
     handleSubmit
    0.06
     learners
    0.06
     MAKE
    0.06
    لاة
    0.06
     GAS
    0.06
     determine
    0.06
    IRST
    0.06
    (:,
    0.06
    Activations Density 0.020%

    No Known Activations