© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 130068
    Prev
    Next
    INDEX
    Explanations

    forum questions and answers

    np_max-act · gemini-2.0-flash

    technical skills and qualifications relevant to job descriptions.

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

    This neuron remains inactive on all shown inputs, indicating it responds only to some rare or specialized pattern not present in these examples.

    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
     boil
    -0.07
    appiness
    -0.06
     satış
    -0.06
    stantiate
    -0.06
     BTN
    -0.06
     오
    -0.06
     Axes
    -0.06
    ा↵↵
    -0.06
     modal
    -0.06
     ()↵
    -0.06
    POSITIVE LOGITS
    लग
    0.07
    (compact
    0.07
    ;",
    0.06
    оф
    0.06
    ltre
    0.06
     stating
    0.06
     clerk
    0.06
     우리는
    0.06
    љ
    0.06
    	driver
    0.06
    Activations Density 0.197%

    No Known Activations