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

    Neuronpedia

    APICircuit 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. 130348
    Prev
    Next
    INDEX
    Explanations

    Statistical data

    np_max-act · gemini-2.0-flash

    information related to health conditions and medical studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by numeric tokens—especially measurements, statistics, and other quantitative values.

    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
     fend
    -0.07
    istle
    -0.07
    坦
    -0.07
     класс
    -0.07
     米
    -0.07
    etas
    -0.06
     hij
    -0.06
     provoz
    -0.06
     Kat
    -0.06
    YLON
    -0.06
    POSITIVE LOGITS
    Few
    0.07
    sey
    0.06
    ORMAL
    0.06
    ,$
    0.06
    SEA
    0.06
    png
    0.06
    .getColumnModel
    0.06
    =""/>↵
    0.06
    _damage
    0.06
     пункт
    0.06
    Activations Density 0.049%

    No Known Activations