© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44389
    Prev
    Next
    INDEX
    Explanations

    Names or legal documents

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on segments of personal names (e.g. tokens within people’s surnames or hyphenated names).

    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
    -radio
    -0.07
     �
    -0.07
     ；
    -0.07
     خاص
    -0.06
     hin
    -0.06
    ’e
    -0.06
     radio
    -0.06
     derby
    -0.06
    _rank
    -0.06
    -your
    -0.06
    POSITIVE LOGITS
    _DIRECT
    0.07
     село
    0.06
    lož
    0.06
    <TEntity
    0.06
     leakage
    0.06
     Below
    0.06
     أيضا
    0.06
    box
    0.06
    Τα
    0.06
    疾
    0.06
    Activations Density 0.113%

    No Known Activations