© 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. 58606
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    This neuron activates on terms used in the body of a question’s problem statement—especially around describing an error or issue (e.g. words like “issue,” “cause,” “this,” etc.).

    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
     некотор
    -0.07
    AFF
    -0.07
    .Sample
    -0.06
     rhs
    -0.06
     SqlParameter
    -0.06
     dance
    -0.06
     arrows
    -0.06
    Live
    -0.06
     چند
    -0.06
    fu
    -0.06
    POSITIVE LOGITS
    _attrib
    0.06
     '',
↵
    0.06
     ند
    0.06
     lang
    0.06
    /org
    0.06
    .Web
    0.06
    Busy
    0.06
     mater
    0.06
    .Notification
    0.06
    ียน
    0.06
    Activations Density 0.050%

    No Known Activations