© 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. 90879
    Prev
    Next
    INDEX
    Explanations

    education

    np_max-act · gemini-2.0-flash

    This neuron detects section-heading phrases that introduce a person’s early life, education, or career (e.g. “Early life and education,” “Education,” or similar biography subsection titles).

    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
     dean
    -0.06
    erde
    -0.06
    .db
    -0.06
    /files
    -0.06
    Qualifier
    -0.06
     consent
    -0.06
    屬
    -0.06
     licence
    -0.06
    ifie
    -0.06
    불
    -0.06
    POSITIVE LOGITS
    _LVL
    0.08
    SQLite
    0.07
     ngăn
    0.07
    chrift
    0.07
    とした
    0.06
    -lat
    0.06
     tem
    0.06
     effortless
    0.06
     tiled
    0.06
    ��
    0.06
    Activations Density 0.005%

    No Known Activations