© 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. 91269
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on question-related tokens (e.g. “what,” “you,” “are,” “asking,” “for”) and so mainly detects when the user is phrasing or clarifying a question.

    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
    .NVarChar
    -0.06
    534
    -0.06
    (bitmap
    -0.06
    耳
    -0.06
     розум
    -0.06
    -shadow
    -0.06
     徒
    -0.06
    .printStackTrace
    -0.06
     Cody
    -0.06
    avě
    -0.06
    POSITIVE LOGITS
    \R
    0.07
    'M
    0.06
    _COLL
    0.06
    /km
    0.06
     `.
    0.06
     eldre
    0.06
     espera
    0.06
    _FILENO
    0.06
     humming
    0.06
    	container
    0.06
    Activations Density 0.030%

    No Known Activations