© 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. 91199
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects field‐definition property names in form schema objects (e.g. hintText, errorText, defaultValue, floatingLabelText).

    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
     ()->
    -0.07
     yanı
    -0.06
     accur
    -0.06
    Den
    -0.06
     filt
    -0.06
     iterations
    -0.06
    !!.
    -0.06
     тру
    -0.06
     (),
    -0.06
     Rak
    -0.06
    POSITIVE LOGITS
    ards
    0.07
     Cash
    0.06
     fleeing
    0.06
    ***/↵
    0.06
     Socket
    0.06
     Hockey
    0.06
     conosc
    0.06
     viewHolder
    0.06
    automatic
    0.06
    -load
    0.06
    Activations Density 0.069%

    No Known Activations