© 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. 7159
    Prev
    Next
    INDEX
    Explanations

    Programming questions/answers

    np_max-act · gemini-2.0-flash

    The neuron fires on the assistant’s polite clarification or “please rephrase/clarify your question” requests.

    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
    HD
    -0.07
     Gos
    -0.06
     خارجی
    -0.06
    Facade
    -0.06
    TP
    -0.06
    ActivityIndicatorView
    -0.06
     raise
    -0.06
    (rawValue
    -0.06
    GLOSS
    -0.06
    �
    -0.05
    POSITIVE LOGITS
    (comm
    0.07
     dob
    0.07
    ibt
    0.07
    ]});↵
    0.07
     ماده
    0.07
    esor
    0.07
    pear
    0.06
    uggestion
    0.06
    %)↵↵
    0.06
    .Canvas
    0.06
    Activations Density 0.058%

    No Known Activations