© 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. 7-RESID-POST-AA
    11. 36133
    Prev
    Next
    INDEX
    Explanations

    current

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the currently active or current context/object (references to the item/page/process that is in effect now).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moll
    -0.07
     penetrating
    -0.07
     annotation
    -0.07
    rien
    -0.07
    漫
    -0.06
     stat
    -0.06
     ADC
    -0.06
     вол
    -0.06
     those
    -0.06
     denying
    -0.06
    POSITIVE LOGITS
    تغ
    0.07
    (current
    0.07
     ReadOnly
    0.07
     tím
    0.07
    _venta
    0.06
    !
↵
    0.06
    __)↵
    0.06
     Walk
    0.06
    ερ
    0.06
     �
    0.06
    Activations Density 0.014%

    No Known Activations