Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12927
    Prev
    Next
    INDEX
    Explanations

    murder cases

    np_max-act · gemini-2.0-flash

    This neuron detects personal names—capitalized proper‐noun references to individuals (e.g., victims or parties) in legal text.

    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
     Мон
    -0.07
    FA
    -0.07
     picnic
    -0.06
     Adrian
    -0.06
     Frontier
    -0.06
    _term
    -0.06
     Qué
    -0.06
     đấu
    -0.06
     icing
    -0.06
     fwd
    -0.06
    POSITIVE LOGITS
    veřej
    0.07
    lean
    0.07
    uesta
    0.06
     column
    0.06
     consectetur
    0.06
    poon
    0.06
    .annotation
    0.06
    (bb
    0.06
     accord
    0.06
     Logged
    0.06
    Activations Density 0.017%

    No Known Activations