© 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. 69000
    Prev
    Next
    INDEX
    Explanations

    policies

    np_max-act · gemini-2.0-flash

    This neuron fires on formal policy‐ and procedure‐type headings and keywords (e.g. “manual,” “policy,” “procedures”) used in compliance or governance documents.

    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
     Nuevo
    -0.07
    Nuevo
    -0.07
    ومتر
    -0.07
    事務
    -0.07
     معنی
    -0.06
    #######
    -0.06
    ++]=
    -0.06
    にして
    -0.06
    (withIdentifier
    -0.06
    宋体
    -0.06
    POSITIVE LOGITS
     Interpret
    0.07
     adap
    0.06
    lli
    0.06
     P
    0.06
     ().
    0.06
     Instant
    0.06
    hte
    0.06
    interpreted
    0.06
    етом
    0.06
     proportional
    0.06
    Activations Density 0.013%

    No Known Activations