© 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
    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. 85808
    Prev
    Next
    INDEX
    Explanations

    self-allowing

    np_max-act · gemini-2.0-flash

    The neuron fires on second-person invitation or imperative words (e.g. “let,” “relax,” “allow,” “release”) that urge the reader/listener to immerse themselves, relax, or give in to sensations.

    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
    รร
    -0.06
     antibody
    -0.06
    лючается
    -0.06
    苦
    -0.06
     Evangel
    -0.06
     Ссылки
    -0.06
     activities
    -0.06
    _logical
    -0.06
    .prepare
    -0.06
     jane
    -0.06
    POSITIVE LOGITS
     तरफ
    0.08
    .NO
    0.07
    Allows
    0.06
    등록
    0.06
    DES
    0.06
    üne
    0.06
     Shops
    0.06
     seized
    0.06
    .ERROR
    0.06
    Ř
    0.06
    Activations Density 0.016%

    No Known Activations