© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56564
    Prev
    Next
    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    This neuron detects instruction or prompt keywords (e.g. “Answer,” “provided,” “context,” “ONLY”) in the text.

    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
     درب
    -0.07
    _Parms
    -0.07
    _logical
    -0.07
    	On
    -0.06
    �
    -0.06
    _street
    -0.06
    -un
    -0.06
    .b
    -0.06
    Demon
    -0.06
    лоп
    -0.06
    POSITIVE LOGITS
     cybersecurity
    0.07
     kaybet
    0.06
    ACK
    0.06
    ，由
    0.06
     Prime
    0.06
     APA
    0.06
     surrender
    0.06
     prime
    0.06
     Yugosl
    0.06
     kultur
    0.06
    Activations Density 0.014%

    No Known Activations