© 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. 15-RESID-POST-AA
    6. 6600
    Prev
    Next
    INDEX
    Explanations

    internet forums/tech topics

    np_max-act · gemini-2.0-flash

    The neuron detects names of communities, groups, organizations and other proper nouns (community/organization mentions).

    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_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
    PLIT
    -0.06
     FUNCTIONS
    -0.06
     concentrated
    -0.06
    agem
    -0.06
     Social
    -0.06
    iana
    -0.06
     ships
    -0.06
     entering
    -0.06
    umbnails
    -0.06
    _tick
    -0.06
    POSITIVE LOGITS
    ACTION
    0.08
    .$
    0.07
     wisely
    0.07
    声明
    0.06
    уются
    0.06
    ANDLE
    0.06
    .,
    0.06
    娜
    0.06
    “그
    0.06
     Winston
    0.06
    Activations Density 0.036%

    No Known Activations