© 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
    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. 7544
    Prev
    Next
    INDEX
    Explanations

    nod

    np_max-act · gemini-2.0-flash

    The neuron activates on nonverbal affirmative cues—especially the token “nodded.”

    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
     نبود
    -0.07
    ">-->↵
    -0.07
     Pres
    -0.06
    成
    -0.06
     ROS
    -0.06
    Ult
    -0.06
     frække
    -0.06
    Security
    -0.06
    >Login
    -0.06
     jets
    -0.06
    POSITIVE LOGITS
    umann
    0.07
    寧
    0.07
    _SIGN
    0.07
     Initialized
    0.07
    δέ
    0.06
     widen
    0.06
    tik
    0.06
    .JsonProperty
    0.06
     �
    0.06
    ocurrency
    0.06
    Activations Density 0.002%

    No Known Activations