© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13159
    Prev
    Next
    INDEX
    Explanations

    routing

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect or respond to any token patterns.

    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
    <{
    -0.06
     tỉ
    -0.06
     ISSN
    -0.06
    appearance
    -0.06
    _factor
    -0.06
    ";↵↵
    -0.06
     แพ
    -0.06
    -add
    -0.06
    /close
    -0.05
     जम
    -0.05
    POSITIVE LOGITS
     Routing
    0.10
     routing
    0.09
     routed
    0.08
     Wichita
    0.07
    INFRINGEMENT
    0.07
     directing
    0.07
    قل
    0.07
    direct
    0.07
    cheduled
    0.07
     drilled
    0.07
    Activations Density 0.010%

    No Known Activations