© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89741
    Prev
    Next
    INDEX
    Explanations

    Petting

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the root “tick” (as in tickle, ticklish, tickling) wherever they appear.

    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
    ْس
    -0.07
     PLAN
    -0.07
    ami
    -0.06
     raid
    -0.06
     blown
    -0.06
     BUS
    -0.06
    gn
    -0.06
     laws
    -0.06
    AM
    -0.06
     Nokia
    -0.06
    POSITIVE LOGITS
    	EIF
    0.07
    ngoing
    0.07
     činnost
    0.06
    liness
    0.06
     Hitch
    0.06
    Located
    0.06
    動
    0.06
     csvfile
    0.06
    _DONE
    0.06
     rugged
    0.06
    Activations Density 0.006%

    No Known Activations