© 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. 7950
    Prev
    Next
    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash

    The neuron fires on Unity YAML metadata field names that begin with an underscore (e.g. “_Object,” “_PrefabInstance,” “_Name,” 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
     využití
    -0.06
     RESPONS
    -0.06
    ột
    -0.06
     Nhĩ
    -0.06
     免
    -0.06
    anky
    -0.05
    صن
    -0.05
    kanı
    -0.05
    かない
    -0.05
    ventario
    -0.05
    POSITIVE LOGITS
     softmax
    0.07
     mower
    0.07
            ↵↵
    0.07
     cứu
    0.07
     καθ
    0.07
    &p
    0.07
     spender
    0.06
    .Identity
    0.06
     Cheryl
    0.06
    (cluster
    0.06
    Activations Density 0.002%

    No Known Activations