© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43538
    Prev
    Next
    INDEX
    Explanations

    Descriptive/instructional language

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens representing decimal‐point numbers (i.e., floating‐point numerals).

    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
     narciss
    -0.06
    ders
    -0.06
    ardon
    -0.06
    .GetUser
    -0.06
    _inicio
    -0.06
     Григор
    -0.06
     гаран
    -0.06
    Training
    -0.06
     tighter
    -0.05
     values
    -0.05
    POSITIVE LOGITS
    改变
    0.07
     altering
    0.07
    اسية
    0.07
    Rob
    0.06
    aat
    0.06
    .dynamic
    0.06
    att
    0.06
     Ever
    0.06
    -changing
    0.06
    ificación
    0.06
    Activations Density 0.080%

    No Known Activations