© 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. 18147
    Prev
    Next
    INDEX
    Explanations

    Friday

    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
     Albert
    -0.07
    avel
    -0.07
     SDL
    -0.07
     maps
    -0.06
     laid
    -0.06
    702
    -0.06
    2
    -0.06
     JL
    -0.06
     UL
    -0.06
     sắp
    -0.06
    POSITIVE LOGITS
     Friday
    0.10
     Thursday
    0.10
    Friday
    0.09
    Thursday
    0.08
     Thurs
    0.08
     thigh
    0.08
     hh
    0.08
    高
    0.08
     Fridays
    0.07
     thu
    0.07
    Activations Density 0.011%

    No Known Activations