© 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. 93357
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on emotionally charged language that signals a character’s inner conflict or personal need.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    narratives involving unconventional body modifications and their consequences.

    oai_token-act-pair · gpt-4o-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
    610
    -0.07
     intrigued
    -0.07
    .setViewportView
    -0.07
     suiv
    -0.06
     Fletcher
    -0.06
    �新
    -0.06
     prio
    -0.06
     Wenger
    -0.06
    マ
    -0.06
     marsh
    -0.06
    POSITIVE LOGITS
    .viewModel
    0.06
     Fasc
    0.06
    /ge
    0.06
     эти
    0.06
     Geometry
    0.06
    __,
    0.06
    /order
    0.06
    Analytics
    0.06
    customer
    0.06
    同じ
    0.06
    Activations Density 0.045%

    No Known Activations