Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8039
    Prev
    Next
    INDEX
    Explanations

    comparing groups in studies

    np_max-act · gemini-2.0-flash

    connections between hormonal responses and eating behavior in disorders.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by decimal numbers (numeric tokens 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
     Wii
    -0.07
    ถม
    -0.06
     PlayStation
    -0.06
    689
    -0.06
    的手
    -0.06
     deadlock
    -0.06
     fractures
    -0.06
     AppBundle
    -0.06
     curs
    -0.06
    19
    -0.06
    POSITIVE LOGITS
     reverted
    0.08
    _nbr
    0.07
     nä
    0.07
    #define
    0.06
    _salt
    0.06
    자기
    0.06
     تس
    0.06
     fade
    0.06
     voleb
    0.06
     SUCCESS
    0.06
    Activations Density 0.012%

    No Known Activations