© 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. 90678
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens (numbers, digits, and numeric quantities).

    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
     zatímco
    -0.07
     Maggie
    -0.06
     Zah
    -0.06
     able
    -0.06
     Violet
    -0.06
     زاد
    -0.06
     figure
    -0.06
     الثاني
    -0.06
     although
    -0.06
     Sophie
    -0.06
    POSITIVE LOGITS
    YD
    0.07
    callback
    0.07
    RY
    0.07
    above
    0.06
    _
    ↵
    0.06
    ADED
    0.06
    IRR
    0.06
    ثر
    0.06
    Factory
    0.06
     acompanh
    0.06
    Activations Density 0.094%

    No Known Activations