© 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. 9385
    Prev
    Next
    INDEX
    Explanations

    Carpets

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to mentions of “carpet” (including its plural and compounds), especially in contexts of carpet cleaning or types of carpets.

    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
     Lexus
    -0.07
     пис
    -0.07
     घटन
    -0.07
    同意
    -0.07
    	com
    -0.06
     Winn
    -0.06
    高校
    -0.06
     transmitted
    -0.06
    science
    -0.06
    insn
    -0.06
    POSITIVE LOGITS
     carpet
    0.15
     carpets
    0.13
     Carpet
    0.12
    aviest
    0.09
    ET
    0.08
    et
    0.08
     Velvet
    0.08
    pet
    0.08
     Rug
    0.07
    επ
    0.07
    Activations Density 0.004%

    No Known Activations