© 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. 124979
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects polite “opt-out” phrases where the text says “do not wish to…” or “do not want to…” as a way of declining an action.

    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
    .dictionary
    -0.07
     postseason
    -0.06
     playoffs
    -0.06
    ありがとうござ
    -0.06
    _AdjustorThunk
    -0.06
     xo
    -0.06
     соп
    -0.06
     �
    -0.06
    disposed
    -0.06
    inizin
    -0.06
    POSITIVE LOGITS
     Py
    0.07
     хорошо
    0.07
     cada
    0.07
     возмож
    0.06
     Mighty
    0.06
    PATH
    0.06
    ayscale
    0.06
     RegExp
    0.06
     notions
    0.06
    .subtract
    0.06
    Activations Density 0.014%

    No Known Activations