© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91551
    Prev
    Next
    INDEX
    Explanations

    Dimensions

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on numeric measurements and dimension specifications (e.g. numbers with units or “x” denoting sizes).

    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
     така
    -0.08
     sonunda
    -0.07
     Falls
    -0.06
     peptide
    -0.06
     museum
    -0.06
     Museum
    -0.06
     类
    -0.06
     득
    -0.06
    _datas
    -0.06
     menn
    -0.06
    POSITIVE LOGITS
    Cipher
    0.06
    ulia
    0.06
    _IV
    0.06
    ich
    0.06
     구성
    0.06
    HOW
    0.06
    重複重複
    0.06
    ＿＿＿
    0.06
    altura
    0.06
     जब
    0.06
    Activations Density 0.002%

    No Known Activations