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. 126482
    Prev
    Next
    INDEX
    Explanations

    cycle

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of motorcycles (and related forms of the word).

    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
     Lease
    -0.07
    引用
    -0.07
     он
    -0.07
     Debbie
    -0.06
     Plans
    -0.06
    (builder
    -0.06
     베스트
    -0.06
    (of
    -0.06
     Families
    -0.06
     Gros
    -0.06
    POSITIVE LOGITS
     motorcycle
    0.07
     DataGridView
    0.07
     strconv
    0.07
     motorcycles
    0.07
    _PRIORITY
    0.06
    uther
    0.06
    esty
    0.06
     Moto
    0.06
     Motorcycle
    0.06
    .toDouble
    0.06
    Activations Density 0.003%

    No Known Activations