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

    Neuronpedia

    Jacobian LensNEW
    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. 37954
    Prev
    Next
    INDEX
    Explanations

    beam

    np_max-act · gemini-2.0-flash

    This neuron fires on the “agi” substring in the context of “Yagi antenna,” effectively detecting mentions of Yagi antennas.

    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
    _Impl
    -0.06
    .fullName
    -0.06
     inherent
    -0.06
    _terms
    -0.06
    logout
    -0.06
    illard
    -0.06
    UV
    -0.06
     alım
    -0.06
     catchError
    -0.06
    業務
    -0.06
    POSITIVE LOGITS
    ivo
    0.07
     �
    0.07
     cube
    0.06
    [Y
    0.06
     hairs
    0.06
    li
    0.06
    )<
    0.06
    <_
    0.06
    ！
    0.06
    　i
    0.06
    Activations Density 0.009%

    No Known Activations