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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 50597
    Prev
    Next
    INDEX
    Explanations

    x

    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
    <unsigned
    -0.06
    Function
    -0.06
     첫
    -0.06
     longitude
    -0.06
     tarde
    -0.06
     Payload
    -0.06
     سبک
    -0.06
    Compact
    -0.06
     Superintendent
    -0.06
    \File
    -0.06
    POSITIVE LOGITS
     Wo
    0.06
    sounds
    0.06
      ̄
    0.06
    .endswith
    0.06
    usic
    0.06
     слова
    0.06
    owo
    0.06
    alış
    0.06
     tongues
    0.06
     iy
    0.06
    Activations Density 0.004%

    No Known Activations