© 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. 3-RESID-POST-AA
    11. 94097
    Prev
    Next
    INDEX
    Explanations

    machine translation, sequence modeling

    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
     pt
    -0.07
    -session
    -0.07
    (bc
    -0.07
    ,file
    -0.07
    값
    -0.07
    復
    -0.06
    space
    -0.06
    placements
    -0.06
     Pract
    -0.06
    563
    -0.06
    POSITIVE LOGITS
     fres
    0.06
     dealloc
    0.06
    цент
    0.06
    LM
    0.06
     roleId
    0.06
     contrasts
    0.06
     shuttle
    0.06
    ്
    0.06
    ابی
    0.05
    manship
    0.05
    Activations Density 0.553%

    No Known Activations