© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12555
    Prev
    Next
    INDEX
    Explanations

    turn

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on the German turn‐taking phrase “an der Reihe ist,” i.e. indications that “it’s [someone]’s turn.”

    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
     radios
    -0.07
     beds
    -0.06
    ρίου
    -0.06
     uncompressed
    -0.06
    ΑΔ
    -0.06
    Weapons
    -0.06
     harmony
    -0.06
     tote
    -0.06
    YLON
    -0.06
    _NORMAL
    -0.06
    POSITIVE LOGITS
    \model
    0.07
    	Iterator
    0.06
     $"{
    0.06
    -controls
    0.06
    .species
    0.06
    _gener
    0.06
     вспом
    0.06
    ंघ
    0.06
    .security
    0.06
     περισσότε
    0.06
    Activations Density 0.005%

    No Known Activations