© 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. 94186
    Prev
    Next
    INDEX
    Explanations

    icultural

    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
     runner
    -0.06
    .im
    -0.06
    =array
    -0.06
     오
    -0.06
     cheese
    -0.06
    upid
    -0.06
     заб
    -0.06
    oy
    -0.06
     verilen
    -0.05
     flat
    -0.05
    POSITIVE LOGITS
    iculture
    0.18
    icultural
    0.17
    icult
    0.09
     regenerated
    0.09
    mond
    0.09
     itemprop
    0.08
    으
    0.07
    ster
    0.07
    ющей
    0.07
    _sector
    0.07
    Activations Density 0.001%

    No Known Activations