Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 109963
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron activates on the opening imperative “Create an adorable and … creature with,” i.e. the start of an image‐generation prompt beginning with “Create an adorable and ….”

    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
    	unsigned
    -0.06
    _sets
    -0.06
    _EXTENDED
    -0.06
    minimal
    -0.06
    (long
    -0.06
     matrices
    -0.06
    .exports
    -0.06
     yönetic
    -0.06
    -table
    -0.06
    HashSet
    -0.06
    POSITIVE LOGITS
     pute
    0.07
     enr
    0.07
     tranny
    0.06
    boa
    0.06
    Ú
    0.06
     inex
    0.06
    _FACTORY
    0.06
     Accord
    0.06
     इक
    0.06
     퍼
    0.06
    Activations Density 0.112%

    No Known Activations