© 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. 41489
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on sequences of digits, i.e. numeric tokens.

    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
     tandem
    -0.07
    allon
    -0.07
    icycle
    -0.07
    .nt
    -0.06
     จ
    -0.06
    eson
    -0.06
    ,p
    -0.06
     sponsorship
    -0.06
     ListNode
    -0.06
     Ma
    -0.06
    POSITIVE LOGITS
    _ARCHIVE
    0.07
    >--}}↵
    0.06
    `);↵
    0.06
    Usu
    0.06
    inaire
    0.06
     Nov
    0.06
    벨
    0.06
    flo
    0.06
     предполаг
    0.06
     Spi
    0.06
    Activations Density 0.038%

    No Known Activations