© 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. 89068
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on internal section-label markers (e.g. “{#s2a=…}”) that appear immediately after headings.

    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
     Singleton
    -0.07
    _PARAMS
    -0.06
    .DELETE
    -0.06
    .enabled
    -0.06
     AGE
    -0.06
    enzie
    -0.06
     ตร
    -0.06
    .menuStrip
    -0.06
    駅徒歩
    -0.06
     Lease
    -0.06
    POSITIVE LOGITS
     котор
    0.07
     cj
    0.07
    하
    0.07
     grap
    0.06
     ngu
    0.06
     pageable
    0.06
     insignificant
    0.06
    mie
    0.06
    keeping
    0.06
     agregar
    0.06
    Activations Density 0.000%

    No Known Activations