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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 100855
    Prev
    Next
    INDEX
    Explanations

    python dataframe

    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
    	User
    -0.07
     further
    -0.07
    Patient
    -0.07
     Manager
    -0.07
    fortunately
    -0.06
     agony
    -0.06
    ]],↵
    -0.06
    ached
    -0.06
     coins
    -0.06
    amaño
    -0.06
    POSITIVE LOGITS
     oto
    0.06
    senha
    0.06
    fillType
    0.06
     ngoại
    0.06
     fill
    0.06
     payer
    0.06
     �
    0.06
     olma
    0.06
    WS
    0.06
     شهری
    0.06
    Activations Density 0.012%

    No Known Activations