© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89178
    Prev
    Next
    INDEX
    Explanations

    Questions and Answers

    np_max-act · gemini-2.0-flash

    terms related to financial accounting and cost analysis concepts.

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

    This neuron activates on financial or business‐accounting terminology and related quantitative expressions.

    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
     Beaver
    -0.07
    <any
    -0.07
    .adv
    -0.07
    unik
    -0.06
     clothing
    -0.06
    ึ
    -0.06
     Babies
    -0.06
    ife
    -0.06
     continuing
    -0.06
     Myers
    -0.06
    POSITIVE LOGITS
    าหาร
    0.07
    自动
    0.07
    aña
    0.07
    南省
    0.06
    ██
    0.06
    书记
    0.06
    \uD
    0.06
     useHistory
    0.06
    ภ
    0.06
    ‰
    0.06
    Activations Density 0.286%

    No Known Activations