Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 15543
    Prev
    Next
    INDEX
    Explanations

    github code/installation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    株式会社
    -0.06
     WHY
    -0.06
    
    -0.06
    杨
    -0.06
    :",↵
    -0.06
     (↵↵
    -0.06
     SharedPreferences
    -0.06
    791
    -0.06
     kt
    -0.06
     går
    -0.06
    POSITIVE LOGITS
    adece
    0.07
    _choice
    0.07
     basit
    0.06
     insisted
    0.06
     approx
    0.06
     FilePath
    0.06
    笑
    0.06
    .confirm
    0.06
    Static
    0.06
    hest
    0.06
    Activations Density 0.019%

    No Known Activations