© 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. 41630
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (integer or decimal literals) in code or markup.

    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
     oversee
    -0.08
     정부
    -0.07
     diseñador
    -0.06
    损
    -0.06
    идент
    -0.06
     الدولي
    -0.06
     smokers
    -0.06
    Thousands
    -0.06
     आस
    -0.06
     Ott
    -0.06
    POSITIVE LOGITS
    gr
    0.07
     DATABASE
    0.06
     prevented
    0.06
    rowned
    0.06
    ी
    0.06
    =value
    0.06
    ترین
    0.06
    .navCtrl
    0.06
    (struct
    0.06
    .Modified
    0.06
    Activations Density 0.209%

    No Known Activations