© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89086
    Prev
    Next
    INDEX
    Explanations

    access control and permissions

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of user‐permission and access‐control setup terms (e.g. “Permission Sets,” “Session-Based Permission Set,” “assign permissions,” “roles,” “ACL,” etc.).

    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
     npm
    -0.07
     Train
    -0.06
     रखन
    -0.06
    .Visual
    -0.06
     Keto
    -0.06
     submar
    -0.06
    _funcs
    -0.06
    logs
    -0.06
    ADIUS
    -0.06
    Software
    -0.06
    POSITIVE LOGITS
    빌
    0.07
     iliş
    0.07
    credit
    0.06
     porte
    0.06
     bloom
    0.06
    ",&
    0.06
     nackte
    0.06
    =").
    0.06
     neob
    0.06
     süresi
    0.06
    Activations Density 0.024%

    No Known Activations