© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30678
    Prev
    Next
    INDEX
    Explanations

    Medical test statistics

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on floating‐point numeric tokens (e.g. “1.38…,” “0.7377…,” “2.3203…”) that report statistical or measurement values.

    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
     pinpoint
    -0.07
     سیاست
    -0.07
     Witch
    -0.06
     Patton
    -0.06
     справа
    -0.06
    olah
    -0.06
    approve
    -0.06
     Barney
    -0.06
     Tib
    -0.06
     GLfloat
    -0.06
    POSITIVE LOGITS
    행
    0.07
     grund
    0.07
    (APP
    0.06
     працівників
    0.06
     UTIL
    0.06
     часом
    0.06
    ensed
    0.06
    ęd
    0.06
    (panel
    0.06
    loha
    0.06
    Activations Density 0.004%

    No Known Activations