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. 122163
    Prev
    Next
    INDEX
    Explanations

    Animal cruelty

    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
    _lower
    -0.07
    _FRAME
    -0.06
     Polish
    -0.06
    倒
    -0.06
    ounder
    -0.06
     Up
    -0.06
     Něm
    -0.06
     UP
    -0.06
    ゲ
    -0.06
    ИТ
    -0.06
    POSITIVE LOGITS
    Thought
    0.07
    .obtain
    0.07
    リ
    0.07
    Ensure
    0.06
    -application
    0.06
    prevent
    0.06
    议
    0.06
    .LogInformation
    0.06
    600
    0.06
    chapter
    0.06
    Activations Density 0.016%

    No Known Activations