© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30027
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects high‐level summary or conclusion markers in text, spotlighting words that signal the key point or overall take-home message.

    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
    erable
    -0.07
    heavy
    -0.07
     strongly
    -0.07
    iterals
    -0.06
     Bhar
    -0.06
    <a
    -0.06
    Others
    -0.06
    ierung
    -0.06
     identifies
    -0.06
    .setLevel
    -0.06
    POSITIVE LOGITS
     Signup
    0.07
     Merch
    0.06
     케이
    0.06
     jub
    0.06
    izoph
    0.06
     Quy
    0.06
    자
    0.06
     році
    0.06
     dấu
    0.06
     loadImage
    0.06
    Activations Density 0.065%

    No Known Activations