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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29575
    Prev
    Next
    INDEX
    Explanations

    anchor

    np_max-act · gemini-2.0-flash

    The neuron activates on HTML anchor‐link constructs and URL‐hash references (e.g. href="#…", name= or id= attributes, location.hash), i.e. internal page “anchor” navigation markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    [ID
    -0.06
    das
    -0.06
     baggage
    -0.06
     cursed
    -0.06
    .real
    -0.06
    .icons
    -0.06
     obligated
    -0.06
     kids
    -0.06
     ordinance
    -0.06
     solicitud
    -0.06
    POSITIVE LOGITS
     hashmap
    0.07
    postgresql
    0.07
    ]-->↵
    0.07
            
    ↵
    ↵
    0.07
     concentrating
    0.07
    maps
    0.07
    occupation
    0.06
    EntityManager
    0.06
    Attendance
    0.06
            
    ↵        
    ↵
    0.06
    Activations Density 0.007%

    No Known Activations