© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 127118
    Prev
    Next
    INDEX
    Explanations

    grip or traction

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of footwear traction features—words like grip, traction, sole, rubber, 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
     Snapchat
    -0.06
    adata
    -0.06
     �
    -0.06
     magnificent
    -0.06
    ريك
    -0.06
    ΕΧ
    -0.06
    もう
    -0.06
    Reuse
    -0.06
    تهم
    -0.06
    ubernetes
    -0.06
    POSITIVE LOGITS
     traction
    0.08
    _GB
    0.07
    进
    0.07
     courte
    0.06
     coun
    0.06
     probation
    0.06
     accomplishment
    0.06
     εμφ
    0.06
     comercial
    0.06
    ा।↵
    0.06
    Activations Density 0.006%

    No Known Activations