© 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. 108880
    Prev
    Next
    INDEX
    Explanations

    programming errors, questions asked

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens involved in asking or referencing questions (words like “what,” “any,” “questions,” etc.).

    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
    die
    -0.07
    vt
    -0.07
     congestion
    -0.06
     matriz
    -0.06
    眠
    -0.06
    ция
    -0.06
    edd
    -0.06
    rxjs
    -0.06
    d
    -0.06
    19
    -0.06
    POSITIVE LOGITS
    _BL
    0.06
    ительность
    0.06
     Suriye
    0.06
     چند
    0.06
    (rd
    0.06
     itemList
    0.06
     MongoDB
    0.06
    _TRANSFER
    0.06
    �
    0.06
     acquainted
    0.06
    Activations Density 0.099%

    No Known Activations