© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77692
    Prev
    Next
    INDEX
    Explanations

    view controllers (code)

    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
             
    -0.06
     IU
    -0.06
     porous
    -0.06
    xBF
    -0.06
    _EVT
    -0.06
            
    ↵        
    ↵
    -0.06
     realmente
    -0.06
    iterr
    -0.06
     udrž
    -0.06
     lev
    -0.06
    POSITIVE LOGITS
    �
    0.07
     getContentPane
    0.06
     Antib
    0.06
     regular
    0.06
    (connect
    0.06
    cks
    0.06
     TestUtils
    0.06
    :maj
    0.06
    にか
    0.06
    .getContentPane
    0.06
    Activations Density 0.011%

    No Known Activations