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. 15-RESID-POST-AA
    6. 31482
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excessive
    -0.06
     dài
    -0.06
     accompanied
    -0.06
    rió
    -0.06
    雑
    -0.06
    zon
    -0.06
     corpses
    -0.06
    ocytes
    -0.06
     LORD
    -0.06
     containerView
    -0.06
    POSITIVE LOGITS
     Path
    0.06
    چی
    0.06
    ertext
    0.06
    .BL
    0.06
     Snape
    0.06
     нож
    0.06
    �s
    0.06
     直
    0.06
     Tech
    0.06
    AdminController
    0.06
    Activations Density 0.015%

    No Known Activations