© 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. 129578
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (numbers containing a decimal point).

    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
    athom
    -0.08
     动
    -0.07
    юсь
    -0.07
    -II
    -0.07
     BitConverter
    -0.06
        
    -0.06
    ファ
    -0.06
     �
    -0.06
    =
    -0.06
    .setPassword
    -0.06
    POSITIVE LOGITS
     coupon
    0.07
    รวจ
    0.07
     Dim
    0.06
     Martha
    0.06
     mismo
    0.06
    477
    0.06
     SDS
    0.06
    selectors
    0.06
     Powell
    0.06
    Validators
    0.06
    Activations Density 0.003%

    No Known Activations