© 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. 68532
    Prev
    Next
    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash

    This neuron detects the en‐dash marking the span between birth and death dates (i.e. the “–” in a lifespan notation).

    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
     Currently
    -0.06
     Jennifer
    -0.06
    aldo
    -0.06
    Firstname
    -0.06
    ерш
    -0.06
    NOW
    -0.06
     Mohammed
    -0.06
    Conflict
    -0.06
    asc
    -0.06
     Newcastle
    -0.06
    POSITIVE LOGITS
     송
    0.07
    紫
    0.07
    ящих
    0.07
     üzer
    0.07
     qué
    0.06
    .RegisterType
    0.06
    .Disabled
    0.06
     kadın
    0.06
     şeyi
    0.06
     papel
    0.06
    Activations Density 0.002%

    No Known Activations