© 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. 128853
    Prev
    Next
    INDEX
    Explanations

    Complex sentences

    np_max-act · gemini-2.0-flash

    This neuron activates on text describing roles and responsibilities, particularly on phrases like “responsible for” that outline who does what.

    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
    itin
    -0.06
     PHYS
    -0.06
          
    -0.06
    Activated
    -0.06
    Parsed
    -0.06
    ивают
    -0.06
    -field
    -0.06
    Kal
    -0.06
    .keys
    -0.06
     X
    -0.06
    POSITIVE LOGITS
     запах
    0.07
    ":"","
    0.07
     $(".
    0.07
    /jquery
    0.07
    ,{"
    0.06
     giá
    0.06
     rež
    0.06
    angstrom
    0.06
     όλ
    0.06
     thương
    0.06
    Activations Density 0.106%

    No Known Activations