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. 36561
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    즘
    -0.07
     Chips
    -0.07
     cabel
    -0.06
     питання
    -0.06
    ='../
    -0.06
     Managing
    -0.06
    staking
    -0.06
    inalg
    -0.06
    ActionCode
    -0.06
     objectType
    -0.06
    POSITIVE LOGITS
    ذكر
    0.07
     freeze
    0.07
     court
    0.06
    PI
    0.06
    )!↵
    0.06
     sen
    0.06
    ο
    0.06
    江
    0.06
     fault
    0.06
     cush
    0.06
    Activations Density 0.063%

    No Known Activations