© 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. 55766
    Prev
    Next
    INDEX
    Explanations

    Programming return values

    np_max-act · gemini-2.0-flash

    The neuron fires on the instruction‐template keywords (e.g. “validate,” “reply,” “with,” “if,” etc.) that frame the user’s semantic‐matching prompt.

    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
    下载次数
    -0.06
    444
    -0.06
     있다는
    -0.06
    /Login
    -0.06
    から
    -0.06
    nivel
    -0.06
     tapered
    -0.06
     Logging
    -0.06
     |/
    -0.06
    (hwnd
    -0.06
    POSITIVE LOGITS
    305
    0.07
     referrals
    0.07
    %%%%%%%%%%%%%%%%
    0.06
    ational
    0.06
    웨어
    0.06
     wrinkles
    0.06
     Afrika
    0.06
    utex
    0.06
     dialogs
    0.06
    cloth
    0.06
    Activations Density 0.014%

    No Known Activations