© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72180
    Prev
    Next
    INDEX
    Explanations

    Broad range of topics

    np_max-act · gemini-2.0-flash

    The neuron activates on domain-relevant content words (key nouns and verbs) rather than on function words or punctuation.

    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
    /swagger
    -0.07
    _MAY
    -0.07
    еліг
    -0.06
    ursal
    -0.06
    кул
    -0.06
    aston
    -0.06
     elegant
    -0.06
     bowel
    -0.06
    uyu
    -0.06
    ente
    -0.06
    POSITIVE LOGITS
    ामन
    0.07
    )>↵
    0.07
     并
    0.07
    GF
    0.06
     vibrations
    0.06
     cuts
    0.06
     replication
    0.06
     decay
    0.06
     renov
    0.06
    umen
    0.06
    Activations Density 0.241%

    No Known Activations