© 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
    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. 72243
    Prev
    Next
    INDEX
    Explanations

    Web page content

    np_max-act · gemini-2.0-flash

    This neuron detects short UI instruction or navigation phrases (imperative verbs and link headers like “To,” “Search,” “Indicate,” 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
     Flatten
    -0.07
    ��
    -0.06
    kich
    -0.06
    hon
    -0.06
    ław
    -0.06
    hammer
    -0.06
    führ
    -0.06
     tanks
    -0.06
    	bus
    -0.06
    ervisor
    -0.06
    POSITIVE LOGITS
    %',
    0.08
    ]";↵
    0.08
    ');
    0.08
     stopping
    0.06
     approaching
    0.06
    .Se
    0.06
     الأد
    0.06
    ]");↵
    0.06
     '/')
    0.06
    ")));↵
    0.06
    Activations Density 0.014%

    No Known Activations