Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84651
    Prev
    Next
    INDEX
    Explanations

    possessives

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the contraction “it’s.”

    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
     Papua
    -0.08
     vì
    -0.08
     відповід
    -0.08
    448
    -0.06
    019
    -0.06
    ाब
    -0.06
    �
    -0.06
    들에게
    -0.06
    namese
    -0.06
    Spl
    -0.06
    POSITIVE LOGITS
    etc
    0.07
    运
    0.07
    _combined
    0.07
    ixo
    0.06
     HeaderComponent
    0.06
    =config
    0.06
    Lng
    0.06
     天
    0.06
    (word
    0.06
     北京
    0.06
    Activations Density 0.015%

    No Known Activations