© 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. 6442
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the Chinese word “可能” (indicating possibility).

    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
     eder
    -0.08
    altet
    -0.06
    achat
    -0.06
     Carter
    -0.06
    omin
    -0.06
     histograms
    -0.06
    ッシュ
    -0.06
    ��作
    -0.06
    gether
    -0.06
    ,it
    -0.06
    POSITIVE LOGITS
    fontWeight
    0.07
     jd
    0.06
    kul
    0.06
    tensorflow
    0.06
     WV
    0.06
    =\"#
    0.06
    aed
    0.06
     profiling
    0.06
    ."'
    0.06
    Season
    0.06
    Activations Density 0.001%

    No Known Activations