© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 49869
    Prev
    Next
    INDEX
    Explanations

    code segments

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是不
    -0.07
     不
    -0.07
    ras
    -0.07
    ФЛ
    -0.07
    abin
    -0.06
     Daten
    -0.06
    ,target
    -0.06
    (selected
    -0.06
    unar
    -0.06
    ارت
    -0.06
    POSITIVE LOGITS
    Vals
    0.06
     Ae
    0.06
    openssl
    0.06
    _mv
    0.06
     wrists
    0.06
     AVL
    0.06
     contractors
    0.06
    measurement
    0.06
     Broncos
    0.06
     Fri
    0.06
    Activations Density 0.001%

    No Known Activations