© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 20868
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     FDA
    -0.07
     Wand
    -0.06
    发展
    -0.06
     thuê
    -0.06
    mus
    -0.06
     wand
    -0.06
    bread
    -0.06
    Serial
    -0.06
     Cleveland
    -0.06
    Inspectable
    -0.06
    POSITIVE LOGITS
     AVAILABLE
    0.07
     正
    0.07
     giant
    0.06
    					↵					↵
    0.06
     movements
    0.06
    <const
    0.06
    .chomp
    0.06
     gadget
    0.06
     USING
    0.06
    _ALREADY
    0.06
    Activations Density 0.017%

    No Known Activations