© 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. 130246
    Prev
    Next
    INDEX
    Explanations

    needs, wants, desires

    np_max-act · gemini-2.0-flash

    This neuron responds to polite hedging or disclaimer phrases (e.g. “However, I would like to point out that…”) in the assistant’s reply.

    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
    guards
    -0.06
     المو
    -0.06
    .Option
    -0.06
     landslide
    -0.06
     fue
    -0.06
    scopes
    -0.06
     درآمد
    -0.06
    urai
    -0.06
    rf
    -0.06
     PriorityQueue
    -0.06
    POSITIVE LOGITS
    :'+
    0.07
    Nach
    0.07
    ้าม
    0.06
    :"<<
    0.06
    !]
    0.06
    !')↵↵
    0.06
    sounds
    0.06
    =:
    0.06
    INUX
    0.06
     chặt
    0.06
    Activations Density 0.027%

    No Known Activations