© 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. 109735
    Prev
    Next
    INDEX
    Explanations

    played

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric and statistical terms—especially counts of games, matches, appearances, or other performance figures.

    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
    ½
    -0.07
    Choices
    -0.06
    Ngh
    -0.06
    .tencent
    -0.06
    کیل
    -0.06
    telephone
    -0.06
    [Int
    -0.06
    (Auth
    -0.06
     стало
    -0.05
    .hits
    -0.05
    POSITIVE LOGITS
     treadmill
    0.07
     electorate
    0.06
     sunshine
    0.06
    ',[
    0.06
     rely
    0.06
     Track
    0.06
     về
    0.06
    deck
    0.06
    gart
    0.06
    .SUB
    0.06
    Activations Density 0.066%

    No Known Activations