© 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 EvalsExportsinterp-engineNEWAPI 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. 102293
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect ordinary natural‐language words (prose/questions) rather than code tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions related to illegal activities and their consequences.

    oai_token-act-pair · gpt-4o-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
    し�
    -0.07
    idos
    -0.06
    �i
    -0.06
    RequiredMixin
    -0.06
    剂
    -0.06
    ilim
    -0.06
    XF
    -0.06
     موجب
    -0.06
    intColor
    -0.06
    Slides
    -0.06
    POSITIVE LOGITS
    stanbul
    0.08
    ,dim
    0.07
     personel
    0.06
     prac
    0.06
     perso
    0.06
     pattern
    0.06
    conf
    0.06
     OK
    0.06
    _format
    0.06
    thesis
    0.06
    Activations Density 0.688%

    No Known Activations