© 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. 57865
    Prev
    Next
    INDEX
    Explanations

    Gold

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized technical terms and proper nouns (model names, theoretical concepts, and abbreviations) in scientific writing.

    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
    _ve
    -0.07
    vier
    -0.07
    hua
    -0.07
    čin
    -0.07
    strar
    -0.06
    ibernate
    -0.06
     holster
    -0.06
     share
    -0.06
    just
    -0.06
     bona
    -0.06
    POSITIVE LOGITS
    (INFO
    0.07
    _Channel
    0.07
    �
    0.07
     scrapped
    0.07
    cantidad
    0.07
    ',↵↵
    0.07
    Cpp
    0.06
     Б
    0.06
     Scala
    0.06
     Seznam
    0.06
    Activations Density 0.029%

    No Known Activations