© 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. 90849
    Prev
    Next
    INDEX
    Explanations

    lists and additions

    np_max-act · gemini-2.0-flash

    The neuron activates on list‐style numeric markers and enumeration tokens (e.g. “1.”, “2.”, “401”, etc.), effectively spotting numbered or enumerated items in the text.

    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
    .HTTP
    -0.07
     Look
    -0.07
     accuses
    -0.07
     monot
    -0.07
    ectors
    -0.07
     Schmidt
    -0.07
    (list
    -0.07
     reaches
    -0.06
     guarantee
    -0.06
     faz
    -0.06
    POSITIVE LOGITS
    _LANGUAGE
    0.06
     Yüz
    0.06
    zelf
    0.06
     Olymp
    0.06
     locally
    0.05
    .semantic
    0.05
    우
    0.05
     FORE
    0.05
     Tennessee
    0.05
     공간
    0.05
    Activations Density 0.055%

    No Known Activations