© 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. 13415
    Prev
    Next
    INDEX
    Explanations

    contribute

    np_max-act · gemini-2.0-flash

    The neuron lights up on verbs and nouns that convey positive support, integration, or contribution—words like “integrate,” “flourish,” “contribute,” “gifts,” and “bring.”

    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
     tık
    -0.07
     foul
    -0.06
    角色
    -0.06
    	async
    -0.06
     outliers
    -0.06
    KIT
    -0.06
    이라고
    -0.06
    杀
    -0.06
     meu
    -0.06
    .AttributeSet
    -0.06
    POSITIVE LOGITS
    aternion
    0.07
     kesinlikle
    0.06
    віт
    0.06
    (ray
    0.06
     النه
    0.06
    .Classes
    0.06
    OperationContract
    0.06
    Setting
    0.06
    ocomplete
    0.06
     Guardians
    0.06
    Activations Density 0.011%

    No Known Activations