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. 7-RESID-POST-AA
    6. 55236
    Prev
    Next
    INDEX
    Explanations

    register

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    v
    -0.07
     Plasma
    -0.07
    VI
    -0.06
     Carnival
    -0.06
    ativ
    -0.06
     Fusion
    -0.06
     plasma
    -0.06
     Fever
    -0.06
     ved
    -0.06
    V
    -0.06
    POSITIVE LOGITS
    Register
    0.11
    register
    0.11
     Register
    0.11
     register
    0.09
     REGISTER
    0.09
     Registers
    0.09
    REGISTER
    0.08
    [right
    0.08
    大學
    0.08
    registers
    0.08
    Activations Density 0.005%

    No Known Activations