© 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. 126800
    Prev
    Next
    INDEX
    Explanations

    system errors and noise

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on domain‐specific process nouns or gerunds—i.e. technical “-ing” words naming methods or procedures.

    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
    ffset
    -0.06
     county
    -0.06
    (ValueError
    -0.06
    .presenter
    -0.06
    تر
    -0.06
    353
    -0.06
     ma
    -0.06
     prima
    -0.06
     Erg
    -0.06
    plotlib
    -0.06
    POSITIVE LOGITS
    Added
    0.07
    ScrollBar
    0.07
     Cec
    0.06
     Spotlight
    0.06
    ности
    0.06
    کی
    0.06
     ATT
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
     interstate
    0.06
     삶
    0.06
    Activations Density 0.054%

    No Known Activations