© 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. 12511
    Prev
    Next
    INDEX
    Explanations

    plus symbol

    np_max-act · gemini-2.0-flash

    mathematical expressions and operations involving square roots.

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

    This neuron responds to occurrences of mathematical expressions, particularly the “sqrt(…)” square‐root notation.

    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
    rabbit
    -0.07
    .animations
    -0.07
     nonprofit
    -0.06
    ukes
    -0.06
     ministry
    -0.06
     Lon
    -0.06
    CompanyId
    -0.06
    跟
    -0.06
    otu
    -0.06
    .U
    -0.06
    POSITIVE LOGITS
    icans
    0.08
     оказ
    0.07
     گاه
    0.07
    Previously
    0.06
    аша
    0.06
    _ITEM
    0.06
     buffs
    0.06
     понима
    0.06
     sessionId
    0.06
    рович
    0.06
    Activations Density 0.015%

    No Known Activations