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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 187
    Prev
    Next
    INDEX
    Explanations

    code/online forum text

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on occurrences of the subordinating conjunction “when.”

    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
     Zuk
    -0.07
     Ramos
    -0.06
     Src
    -0.06
     annoyance
    -0.06
     Pregnancy
    -0.06
     امید
    -0.06
     پیش
    -0.06
     ポ
    -0.06
    applicant
    -0.06
     имеет
    -0.06
    POSITIVE LOGITS
    _Select
    0.07
    XXXXXXXX
    0.06
     -*-
    0.06
    istrate
    0.06
     initialise
    0.06
    []=
    0.06
    ornings
    0.06
     그녀
    0.06
    +len
    0.06
    odor
    0.06
    Activations Density 0.001%

    No Known Activations