© 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. 54427
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “for” (marking purpose or intended use) and closely related purpose‐introducing verb forms.

    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
    .shtml
    -0.07
    	grid
    -0.07
    PDF
    -0.06
     binary
    -0.06
    meye
    -0.06
    ipay
    -0.06
     salmon
    -0.06
     Bakan
    -0.06
     GOLD
    -0.06
    bilir
    -0.06
    POSITIVE LOGITS
    ={↵
    0.07
     вып
    0.07
    astes
    0.07
    (strip
    0.07
     кол
    0.06
    ▍▍
    0.06
     используют
    0.06
     пы
    0.06
     توجه
    0.06
    _angle
    0.06
    Activations Density 0.117%

    No Known Activations