© 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
    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. 43291
    Prev
    Next
    INDEX
    Explanations

    versus

    np_max-act · gemini-2.0-flash

    The neuron activates on the “versus” in court‐case captions (i.e. the “Plaintiff – Appellee, versus Defendant – Appellant” header).

    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
     rates
    -0.07
    $data
    -0.06
     Corner
    -0.06
     Giang
    -0.06
     ostat
    -0.06
     гід
    -0.06
    รายการ
    -0.06
     azi
    -0.06
     sealing
    -0.06
    /tools
    -0.06
    POSITIVE LOGITS
    agos
    0.06
     Verified
    0.06
     april
    0.06
    Specifies
    0.06
     český
    0.06
    commercial
    0.06
     꼭
    0.06
    ossible
    0.06
    :"",
    0.06
    aos
    0.06
    Activations Density 0.005%

    No Known Activations