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. 34536
    Prev
    Next
    INDEX
    Explanations

    robbery

    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
    	width
    -0.06
     �
    -0.06
    038
    -0.06
    plans
    -0.06
     Catalonia
    -0.06
     CUR
    -0.06
     UNICODE
    -0.06
     Kra
    -0.06
    Call
    -0.06
    Cast
    -0.06
    POSITIVE LOGITS
    Jacob
    0.06
    ражд
    0.06
    luent
    0.06
    .dependencies
    0.06
     robbery
    0.06
     peque
    0.06
    /sl
    0.06
    ropp
    0.06
     Donne
    0.06
     robber
    0.06
    Activations Density 0.005%

    No Known Activations