© 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. 68869
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron triggers on the assistant’s stock disclaimer that it is an AI language model “with no personal beliefs or opinions.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mentions of war-related topics and conflicts involving East Asia.

    oai_token-act-pair · gpt-4o-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
    �
    -0.07
    声音
    -0.07
    	gr
    -0.07
     Chips
    -0.06
    Token
    -0.06
    Aws
    -0.06
    илання
    -0.06
     your
    -0.06
    odial
    -0.06
    όν
    -0.06
    POSITIVE LOGITS
     xlink
    0.06
    /sources
    0.06
    ('*
    0.06
     VB
    0.06
    Neither
    0.06
     SECTION
    0.06
    届
    0.06
     Bihar
    0.06
    ơ
    0.06
     YM
    0.06
    Activations Density 0.024%

    No Known Activations