© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126710
    Prev
    Next
    INDEX
    Explanations

    snuggling

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases that evoke cozy, cuddly, or snuggling moments (like “snuggle,” “cozy,” “curl up,” “rocking,” 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
     pager
    -0.07
    Expense
    -0.07
    Been
    -0.07
     baked
    -0.06
    	to
    -0.06
     رای
    -0.06
     интер
    -0.06
     spat
    -0.06
     lawmaker
    -0.06
     astore
    -0.06
    POSITIVE LOGITS
    ühl
    0.07
     cozy
    0.07
     essentials
    0.07
    DY
    0.07
                                                                    
    0.07
     twitch
    0.06
    GU
    0.06
     snug
    0.06
    ZO
    0.06
    TLS
    0.06
    Activations Density 0.007%

    No Known Activations