© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25198
    Prev
    Next
    INDEX
    Explanations

    database conflict/duplicate handling

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    比例
    -0.07
     geil
    -0.07
     Releases
    -0.07
    次数
    -0.06
    :Number
    -0.06
     coc
    -0.06
     Tutorial
    -0.06
    		 ↵
    -0.06
    _indicator
    -0.06
    aturday
    -0.06
    POSITIVE LOGITS
    dy
    0.07
     Pek
    0.06
     unbearable
    0.06
    .pe
    0.06
    _md
    0.06
     छ
    0.06
    保障
    0.06
     savedInstanceState
    0.06
    .oauth
    0.06
    τυ
    0.06
    Activations Density 0.020%

    No Known Activations