© 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. 12655
    Prev
    Next
    INDEX
    Explanations

    size/age comparisons

    np_max-act · gemini-2.0-flash

    The neuron detects comparative or superlative descriptors (like “larger,” “smaller,” “older,” “younger,” “narrowest,” “deepest”) that indicate relative size, age, or degree.

    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
    내
    -0.07
    "bytes
    -0.07
    ộng
    -0.07
    ்
    -0.06
     Ridge
    -0.06
     tally
    -0.06
    іту
    -0.06
    auction
    -0.06
    STRUCTIONS
    -0.06
    (raw
    -0.06
    POSITIVE LOGITS
    vod
    0.07
     Пер
    0.07
     περ
    0.07
     klass
    0.06
    .comm
    0.06
    -needed
    0.06
     гиб
    0.06
    nim
    0.06
    ρε
    0.06
     bree
    0.06
    Activations Density 0.058%

    No Known Activations