© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76935
    Prev
    Next
    INDEX
    Explanations

    the

    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
    FAILURE
    -0.08
    .Counter
    -0.07
     З
    -0.06
    成绩
    -0.06
    selling
    -0.06
    ัด
    -0.06
    texts
    -0.06
     licence
    -0.06
    deniz
    -0.06
    etroit
    -0.06
    POSITIVE LOGITS
    有什么
    0.07
     viv
    0.06
     мил
    0.06
     emit
    0.06
    Oh
    0.06
     nef
    0.06
     mercenaries
    0.06
     Habit
    0.06
    mamız
    0.06
     dafür
    0.06
    Activations Density 0.179%

    No Known Activations