© 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. 38335
    Prev
    Next
    INDEX
    Explanations

    Scientific/Legal documents

    np_max-act · gemini-2.0-flash

    This neuron never activates (all activation values are zero), so it does not detect any specific text pattern. In other words, it appears to be a “dead” neuron that never fires.

    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
     συμβ
    -0.07
     connectivity
    -0.07
     Schw
    -0.06
    녀
    -0.06
    -cn
    -0.06
     badly
    -0.06
    sap
    -0.06
     descendant
    -0.06
    IZE
    -0.06
     Connectivity
    -0.06
    POSITIVE LOGITS
    (currency
    0.07
     viol
    0.07
     önemlidir
    0.07
    .btnCancel
    0.06
    _nil
    0.06
    řaz
    0.06
    dain
    0.06
    .setImage
    0.06
    ...
    0.06
     Коли
    0.06
    Activations Density 0.001%

    No Known Activations