© 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. 42512
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on the demonstrative pronoun “this,” especially in commands or invitations (e.g. “Watch this,” “Copy this,” “Get this…”).

    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
    Spanish
    -0.07
     shutter
    -0.07
    Pred
    -0.07
    Blood
    -0.06
    ELEMENT
    -0.06
    受到
    -0.06
     photographers
    -0.06
    uzzle
    -0.06
    Dark
    -0.06
     setup
    -0.06
    POSITIVE LOGITS
    307
    0.07
     this
    0.07
    acas
    0.06
    лен
    0.06
    .Office
    0.06
    тів
    0.06
     EV
    0.06
    άβ
    0.06
    alties
    0.06
    าษฎ
    0.06
    Activations Density 0.020%

    No Known Activations