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. 11-RESID-POST-AA
    6. 122714
    Prev
    Next
    INDEX
    Explanations

    Text 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
    QUIRE
    -0.06
     Kara
    -0.06
    ě
    -0.06
     Coun
    -0.06
     praw
    -0.06
    amba
    -0.06
     Occupation
    -0.06
    adastrar
    -0.06
     Adams
    -0.06
     Ali
    -0.06
    POSITIVE LOGITS
     lob
    0.08
    	lbl
    0.07
    =model
    0.07
    ило
    0.06
    ‌دان
    0.06
    full
    0.06
     LAST
    0.06
     BIN
    0.06
    ,UnityEngine
    0.06
     BREAK
    0.06
    Activations Density 0.112%

    No Known Activations