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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 43378
    Prev
    Next
    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on fragments of proper names—that is, on parts of personal (and occasionally place) names.

    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
     cores
    -0.08
    /qt
    -0.07
    وبة
    -0.07
    软件
    -0.07
    /off
    -0.07
     abduction
    -0.07
    III
    -0.07
     blows
    -0.07
     Accessories
    -0.06
     kits
    -0.06
    POSITIVE LOGITS
     trest
    0.06
     totalmente
    0.06
     أج
    0.06
     omn
    0.06
     paperback
    0.06
    :)];↵
    0.06
    ]})↵
    0.06
    Nİ
    0.06
    ´
    0.06
     agreg
    0.06
    Activations Density 0.098%

    No Known Activations