© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128733
    Prev
    Next
    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash

    This neuron detects expressions of possession or ownership, especially “call (one’s) own” as in “a home to call his own.”

    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
     Cove
    -0.08
     Pipeline
    -0.07
     比
    -0.07
     пог
    -0.06
    Atomic
    -0.06
     indu
    -0.06
     тверд
    -0.06
    ครง
    -0.06
     nihil
    -0.06
     Try
    -0.06
    POSITIVE LOGITS
     comfy
    0.06
     homes
    0.06
     ought
    0.06
    _trampoline
    0.06
    .n
    0.06
     home
    0.06
    Should
    0.06
    IEL
    0.05
    aken
    0.05
     kendisi
    0.05
    Activations Density 0.023%

    No Known Activations