© 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. 42969
    Prev
    Next
    INDEX
    Explanations

    start of sentences and quotes

    np_max-act · gemini-2.0-flash

    This neuron detects French-style negation constructions (e.g. “ne… pas,” “n’y… plus,” explicit “plus rien”).

    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
     культури
    -0.07
     температуры
    -0.06
    ormap
    -0.06
    _Password
    -0.06
    aktu
    -0.06
     приступ
    -0.06
    资料
    -0.06
    aviours
    -0.06
    apixel
    -0.06
    DataReader
    -0.06
    POSITIVE LOGITS
     profund
    0.07
    .cont
    0.07
     designs
    0.06
    -present
    0.06
    _missing
    0.06
     #+#
    0.06
    770
    0.06
     midterm
    0.06
     personn
    0.06
     reshape
    0.06
    Activations Density 0.134%

    No Known Activations