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. 125346
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are floating‐point numbers (i.e., numeric strings containing a decimal point).

    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
    NSURL
    -0.06
    :%
    -0.06
    AntiForgeryToken
    -0.06
     öğretmen
    -0.06
    irut
    -0.06
     fatigue
    -0.06
    riteria
    -0.06
     cihaz
    -0.06
    faker
    -0.05
     hovering
    -0.05
    POSITIVE LOGITS
    hood
    0.08
     Reserve
    0.07
    hidden
    0.06
    iero
    0.06
    SECTION
    0.06
    licos
    0.06
     sink
    0.06
     مركز
    0.06
    sted
    0.06
    ...↵↵↵
    0.06
    Activations Density 0.005%

    No Known Activations