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. 19-RESID-POST-AA
    6. 59178
    Prev
    Next
    INDEX
    Explanations

    code examples and how-to prompts

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssue
    -0.06
    ž
    -0.06
    杨
    -0.06
     checker
    -0.06
    Rails
    -0.06
    _argv
    -0.06
     mud
    -0.06
     không
    -0.06
    Disposed
    -0.06
     Identified
    -0.06
    POSITIVE LOGITS
    (repository
    0.08
    RESSION
    0.07
    풍
    0.07
     Successful
    0.07
    (dialog
    0.07
     abandon
    0.07
    	link
    0.06
     Look
    0.06
     successful
    0.06
    _inc
    0.06
    Activations Density 0.000%

    No Known Activations