© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72712
    Prev
    Next
    INDEX
    Explanations

    fun

    np_max-act · gemini-2.0-flash

    long, descriptive introductions about personal experiences or participation in specific activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words and phrases expressing enjoyment or fun—e.g. “fun,” “enjoy,” “have fun,” 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
    .token
    -0.07
    我们
    -0.07
     LinearLayout
    -0.07
    .fasterxml
    -0.06
    /cli
    -0.06
    _HELP
    -0.06
    WindowText
    -0.06
     refuge
    -0.06
     техніч
    -0.06
     touching
    -0.06
    POSITIVE LOGITS
     enjoyment
    0.07
     enjoyable
    0.07
    inate
    0.07
    पर
    0.07
     sx
    0.06
     plunged
    0.06
    osome
    0.06
     Bs
    0.06
     çay
    0.06
     Bj
    0.06
    Activations Density 0.040%

    No Known Activations