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. 23-RESID-POST-AA
    6. 103986
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saddle
    -0.07
     nên
    -0.07
         
    -0.07
     seldom
    -0.07
    юн
    -0.06
    ванов
    -0.06
    	Editor
    -0.06
     виник
    -0.06
     möchte
    -0.06
    /spec
    -0.06
    POSITIVE LOGITS
    iselect
    0.07
    -den
    0.07
    跌
    0.06
    ์ช
    0.06
    .WebControls
    0.06
    agues
    0.06
     definite
    0.06
     intimate
    0.06
    دی
    0.06
    kits
    0.06
    Activations Density 0.183%

    No Known Activations