© 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. 55386
    Prev
    Next
    INDEX
    Explanations

    age/time

    np_max-act · gemini-2.0-flash

    The neuron identifies numeric tokens—especially numbers and quantitative measurements.

    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
    scheme
    -0.07
     Sanat
    -0.07
    ยา
    -0.07
    Ж
    -0.06
     těchto
    -0.06
     Cristina
    -0.06
     accidental
    -0.06
    };
    ↵
    ↵
    ↵
    -0.06
    HD
    -0.06
    腦
    -0.06
    POSITIVE LOGITS
     beacon
    0.07
     imu
    0.07
     technological
    0.06
     UIResponder
    0.06
    .News
    0.06
    Spawn
    0.06
    spr
    0.06
     integer
    0.06
     lông
    0.06
     loneliness
    0.06
    Activations Density 0.042%

    No Known Activations