© 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. 30881
    Prev
    Next
    INDEX
    Explanations

    Scientific experiments

    np_max-act · gemini-2.0-flash

    This neuron detects high-level research signpost terms—words that introduce or describe the scientific study’s objectives, methods, and findings (e.g. study, objective, investigate, experiment).

    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
    ková
    -0.07
    _tc
    -0.07
     کاملا
    -0.07
    ันว
    -0.06
    ár
    -0.06
    LP
    -0.06
     streams
    -0.06
    .scala
    -0.06
    　　　　 　 　
    -0.06
    .pth
    -0.06
    POSITIVE LOGITS
    .Design
    0.07
    药
    0.06
    /**
    0.06
    	gl
    0.06
     gi�
    0.06
     +=
    0.06
     rallying
    0.06
     frat
    0.06
    strstr
    0.06
    (btn
    0.06
    Activations Density 0.037%

    No Known Activations