© 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 EvalsExportsinterp-engineNEWAPI 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. 58204
    Prev
    Next
    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the coordinating conjunction “and” (especially in “and a” linking phrases).

    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
     globally
    -0.06
    Popover
    -0.06
    _buf
    -0.06
    \Container
    -0.06
    нд
    -0.06
     trem
    -0.06
    &_
    -0.06
    _ID
    -0.06
    Normals
    -0.06
    ])↵↵
    -0.06
    POSITIVE LOGITS
    اسة
    0.06
    ويك
    0.06
     getItem
    0.06
    signed
    0.06
    FINE
    0.06
    PushButton
    0.06
     смерть
    0.06
     Importance
    0.06
    ington
    0.06
     MSI
    0.06
    Activations Density 0.120%

    No Known Activations