© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55759
    Prev
    Next
    INDEX
    Explanations

    industrialization

    np_max-act · gemini-2.0-flash

    terms related to the Industrial Revolution, particularly focusing on advancements in technology and production methods.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is sensitive to prominent topic‐specific keywords—especially capitalized or domain-specific nouns like “Industrial” and “Revolution.”

    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
    AAD
    -0.08
    čil
    -0.07
    -outline
    -0.06
    772
    -0.06
     ceramic
    -0.06
     picnic
    -0.06
    ázal
    -0.06
    .write
    -0.06
     Keywords
    -0.06
    pieces
    -0.06
    POSITIVE LOGITS
    наслід
    0.06
     stupidity
    0.06
     lagi
    0.06
     限
    0.06
    whatever
    0.06
    ют
    0.06
    ického
    0.06
     شیر
    0.06
    цес
    0.06
    دیگر
    0.05
    Activations Density 0.029%

    No Known Activations