© 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. 7-RESID-POST-AA
    6. 76908
    Prev
    Next
    INDEX
    Explanations

    Original and specially created works

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that signal material was produced or created for a specific purpose or occasion (words indicating something was made, recorded, composed, or specially prepared).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    million
    -0.09
     nama
    -0.07
    جات
    -0.07
     fueled
    -0.06
     drž
    -0.06
    ansen
    -0.06
    -operator
    -0.06
    	glut
    -0.06
    xito
    -0.06
    anas
    -0.06
    POSITIVE LOGITS
    募
    0.07
    _DBG
    0.06
    責
    0.06
     ROT
    0.06
    .Fat
    0.06
     '').
    0.06
    ]='
    0.06
     {};
    0.06
     investigating
    0.06
    _PRI
    0.06
    Activations Density 0.140%

    No Known Activations