© 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. 129579
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron responds to words (and their forms) that express the idea of preparing or getting ready.

    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
     merge
    -0.07
     boat
    -0.06
     buurt
    -0.06
     trial
    -0.06
    O
    -0.06
    _seek
    -0.06
    oucher
    -0.06
     slashing
    -0.06
    sales
    -0.06
    [block
    -0.06
    POSITIVE LOGITS
    、今
    0.06
    生的
    0.06
     neler
    0.06
    ありがとう
    0.06
     الرياض
    0.06
     와
    0.06
    enance
    0.06
    的情况
    0.06
     roleId
    0.06
    (eval
    0.06
    Activations Density 0.017%

    No Known Activations