© 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. 126252
    Prev
    Next
    INDEX
    Explanations

    names of people

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on personal names (people’s first and/or last 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
    کار
    -0.07
     libero
    -0.07
    摘要
    -0.06
    �
    -0.06
     웨
    -0.06
     With
    -0.06
    Viewer
    -0.06
    Aud
    -0.06
     قهر
    -0.06
    FINE
    -0.06
    POSITIVE LOGITS
    arty
    0.06
    texts
    0.06
     compens
    0.06
    `${
    0.06
    alias
    0.06
    aseline
    0.06
    _tac
    0.06
     cái
    0.06
    алист
    0.06
     ellipse
    0.06
    Activations Density 0.059%

    No Known Activations