© 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. 15-RESID-POST-AA
    11. 22465
    Prev
    Next
    INDEX
    Explanations

    reports/incidents

    np_max-act · gemini-2.0-flash

    This neuron detects formal incident‑report / root‑cause analysis phrasing and document structure in technical reports.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دادن
    -0.07
    RelativeTo
    -0.07
    ension
    -0.07
     внутріш
    -0.06
    -й
    -0.06
    crast
    -0.06
    [G
    -0.06
    ていない
    -0.06
    -append
    -0.06
     purse
    -0.06
    POSITIVE LOGITS
    UILDER
    0.06
    견
    0.06
    _lhs
    0.06
    secs
    0.06
    usiness
    0.06
     Vatican
    0.06
     lodash
    0.06
    ucchini
    0.06
    ibo
    0.06
     USPS
    0.05
    Activations Density 0.021%

    No Known Activations