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. 26244
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
     deleted
    -0.07
    anned
    -0.07
    imized
    -0.07
    广
    -0.07
     intercepted
    -0.06
     guerr
    -0.06
    emd
    -0.06
     Clarence
    -0.06
     depends
    -0.06
    owl
    -0.06
    POSITIVE LOGITS
    .Visual
    0.07
     Böylece
    0.07
     Geschichte
    0.06
     Organizer
    0.06
    :'.$
    0.06
     multicast
    0.06
     TWO
    0.06
    		      
    0.06
     Backpack
    0.06
    !=
    0.06
    Activations Density 0.017%

    No Known Activations