© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 45866
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    Preferences
    -0.07
     oleh
    -0.07
     ÜNİVERSİTESİ
    -0.07
     дал
    -0.06
     LANG
    -0.06
    _multiply
    -0.06
    Με
    -0.06
     mind
    -0.06
     прев
    -0.06
     <<
    -0.06
    POSITIVE LOGITS
     waved
    0.07
     fisheries
    0.07
     philosoph
    0.06
     spec
    0.06
    come
    0.06
     yaptığı
    0.06
     fabrics
    0.06
    (Operation
    0.06
    .comm
    0.06
     عاش
    0.06
    Activations Density 0.020%

    No Known Activations