© 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. 110145
    Prev
    Next
    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash

    This neuron spotlights section‐header or label tokens (e.g. “Summary,” “Le résumé,” “Стишок,” “Poem,” etc.) 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
     تنظیم
    -0.07
     shameful
    -0.07
     ion
    -0.06
    TabPage
    -0.06
       
↵
    -0.06
     ones
    -0.06
     mmc
    -0.06
     bana
    -0.06
    packages
    -0.06
     Lemma
    -0.06
    POSITIVE LOGITS
     royalty
    0.06
    _ef
    0.06
     unpl
    0.06
    �
    0.06
    овід
    0.06
    splash
    0.06
    نم
    0.06
    抽
    0.05
    顶
    0.05
    =r
    0.05
    Activations Density 0.058%

    No Known Activations