© 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. 91102
    Prev
    Next
    INDEX
    Explanations

    premise

    np_max-act · gemini-2.0-flash

    The neuron is specifically detecting occurrences of the word “premise.”

    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
     сообщ
    -0.07
     Джон
    -0.07
     voll
    -0.07
    lerdir
    -0.07
    ัฒนา
    -0.06
     stagger
    -0.06
     almış
    -0.06
     والن
    -0.06
    .onPause
    -0.06
     harmon
    -0.06
    POSITIVE LOGITS
     premise
    0.08
    _stmt
    0.06
    amet
    0.06
     base
    0.06
     concept
    0.06
    _ENDPOINT
    0.06
     mey
    0.06
     선수
    0.06
    feeding
    0.06
    base
    0.06
    Activations Density 0.004%

    No Known Activations