© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68769
    Prev
    Next
    INDEX
    Explanations

    harm or damage

    np_max-act · gemini-2.0-flash

    The neuron fires on language that signals risk, harm, or liability (e.g. danger, nuisance, harm, responsibility).

    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
    าฟ
    -0.08
     celebrities
    -0.06
    ห
    -0.06
     Huawei
    -0.06
    ávající
    -0.06
     sparks
    -0.06
     lParam
    -0.06
    _OFFSET
    -0.06
     yıllarda
    -0.06
     knih
    -0.06
    POSITIVE LOGITS
    (dirname
    0.07
    носи
    0.06
     adı
    0.06
    که
    0.06
    ige
    0.06
    基本
    0.06
     Güven
    0.06
    .mdl
    0.06
     showToast
    0.06
     нада
    0.06
    Activations Density 0.103%

    No Known Activations